Triple
T7154967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MODS |
E166785
|
entity |
| Predicate | hasVersion |
P455
|
FINISHED |
| Object | MODS 3.3 |
E605020
|
NE FINISHED |
How this triple was built (2 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: MODS 3.3 | Statement: [MODS, hasVersion, MODS 3.3]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MODS 3.3 Context triple: [MODS, hasVersion, MODS 3.3]
-
A.
MODS
MODS (Metadata Object Description Schema) is a bibliographic metadata standard developed by the Library of Congress that provides a rich, XML-based format for describing digital and print resources.
-
B.
KMOD
KMOD is the ICAO airport code for Modesto City–County Airport in Modesto, California.
-
C.
Modulen
Modulen is a specialized medical nutrition product line from Nestlé Health Science, commonly used in the dietary management of conditions such as Crohn’s disease.
-
D.
Modula-3
Modula-3 is a systems programming language designed as a safer, more modern successor to Modula-2, emphasizing strong typing, modularity, and support for concurrency and garbage collection.
-
E.
MODS (Metadata Object Description Schema)
chosen
MODS (Metadata Object Description Schema) is an XML-based bibliographic description standard designed to provide a flexible, user-friendly alternative to MARC for describing and sharing library and cultural heritage resources.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69c68887a5cc8190bec0ea96227164f7 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e80c747c8190a017a2b1c3e78a3f |
completed | March 27, 2026, 8:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7bf817e4c819098268479f3fb181f |
completed | March 28, 2026, 11:46 a.m. |
Created at: March 27, 2026, 2:47 p.m.