Triple
T6387535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crystallographic Information Framework |
E143736
|
entity |
| Predicate | relatedStandard |
P37
|
FINISHED |
| Object |
STAR File syntax
STAR File syntax is a flexible, text-based data format used in crystallography and related sciences to store structured experimental and structural information in a machine-readable way.
|
E591485
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: STAR File syntax | Statement: [Crystallographic Information Framework, relatedStandard, STAR File syntax]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: STAR File syntax Context triple: [Crystallographic Information Framework, relatedStandard, STAR File syntax]
-
A.
Lisa File System
Lisa File System is the proprietary disk file system developed by Apple for its early Lisa computer, featuring a hierarchical directory structure and advanced metadata for its time.
-
B.
TFile
TFile is a ROOT framework class that provides an interface for creating, reading, and writing ROOT data files used in high-energy physics and data analysis.
-
C.
S-record
S-record is a Motorola-defined ASCII-based file format used to represent binary data for programming and transferring data to microcontrollers and other embedded systems.
-
D.
File on 4
File on 4 is a long-running BBC Radio 4 investigative journalism programme known for in-depth reports on current affairs, public policy, and social issues.
-
E.
File Allocation Table
The File Allocation Table (FAT) is a simple, widely used file system architecture that tracks the allocation and organization of files on disk storage, commonly employed in older and removable storage devices.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: STAR File syntax Triple: [Crystallographic Information Framework, relatedStandard, STAR File syntax]
Generated description
STAR File syntax is a flexible, text-based data format used in crystallography and related sciences to store structured experimental and structural information in a machine-readable way.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: STAR File syntax Target entity description: STAR File syntax is a flexible, text-based data format used in crystallography and related sciences to store structured experimental and structural information in a machine-readable way.
-
A.
Lisa File System
Lisa File System is the proprietary disk file system developed by Apple for its early Lisa computer, featuring a hierarchical directory structure and advanced metadata for its time.
-
B.
TFile
TFile is a ROOT framework class that provides an interface for creating, reading, and writing ROOT data files used in high-energy physics and data analysis.
-
C.
S-record
S-record is a Motorola-defined ASCII-based file format used to represent binary data for programming and transferring data to microcontrollers and other embedded systems.
-
D.
File on 4
File on 4 is a long-running BBC Radio 4 investigative journalism programme known for in-depth reports on current affairs, public policy, and social issues.
-
E.
File Allocation Table
The File Allocation Table (FAT) is a simple, widely used file system architecture that tracks the allocation and organization of files on disk storage, commonly employed in older and removable storage devices.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c008dac1ec81909cef8157ccd69962 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06869dfb88190aeb84c6c61414888 |
completed | March 22, 2026, 10:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6387dc8888190ba63efcc9aff41b2 |
completed | March 27, 2026, 7:57 a.m. |
| NEDg | Description generation | batch_69c63b0165ac8190bb6001504d4abfcc |
completed | March 27, 2026, 8:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c63b6373e88190b676ee85be8c06fb |
completed | March 27, 2026, 8:10 a.m. |
Created at: March 22, 2026, 4:34 p.m.