Triple
T12128724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IBM 650 |
E288875
|
entity |
| Predicate | dataInputFormat |
P90391
|
FINISHED |
| Object | 80-column punched cards |
—
|
LITERAL 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: 80-column punched cards | Statement: [IBM 650, dataInputFormat, 80-column punched cards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataInputFormat Context triple: [IBM 650, dataInputFormat, 80-column punched cards]
-
A.
primaryInputFormat
chosen
Indicates the data format that is expected or used as the main input for a given process, system, or operation.
-
B.
commandInputFormat
Indicates the expected structure or syntax that a command must follow when being provided as input.
-
C.
storageFormat
Indicates the specific way in which data or content is physically or logically organized, encoded, and stored.
-
D.
dataTypes
Indicates that one entity specifies or defines the kinds or formats of data that are valid or expected for another entity.
-
E.
dataFile
Indicates a relationship where one entity serves as or is associated with a specific data file used, stored, or referenced by another entity.
- F. None of above.
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_69d6ab4b5e4c81909950b17151eb0951 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91841615c819097f20a7447a1b8f4 |
completed | April 10, 2026, 3:33 p.m. |
| PD | Predicate disambiguation | batch_69d91508f8008190b3a90ec0bf0953ca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:49 p.m.