Triple
T3932763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Cohen |
E90832
|
entity |
| Predicate | positionHeldForPeriod |
P38592
|
FINISHED |
| Object | United States Secretary of Defense from 1997 to 2001 |
—
|
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: United States Secretary of Defense from 1997 to 2001 | Statement: [William Cohen, positionHeldForPeriod, United States Secretary of Defense from 1997 to 2001]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionHeldForPeriod Context triple: [William Cohen, positionHeldForPeriod, United States Secretary of Defense from 1997 to 2001]
-
A.
positionHeld
Indicates that an entity occupies or has occupied a specific role, job, office, or position within an organization or context.
-
B.
usualMonthHeld
Indicates the month in which an event or activity is typically or customarily held.
-
C.
holdsStakeThrough
Indicates that one entity possesses an ownership interest in another entity indirectly, via an intermediate entity or instrument.
-
D.
lastHeldIn
Indicates that an event or state most recently took place or was hosted in a particular location or context.
-
E.
titleHeldDuringPeriod
chosen
Indicates that an entity held a specific title or position for the duration of a given time period.
- 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_69aed95f26e0819094b0e71974543a19 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeedaaf3c881909539831bf3a8bf10 |
completed | March 9, 2026, 3:56 p.m. |
| PD | Predicate disambiguation | batch_69aee7625ad4819097e4e8a168c19274 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:23 p.m.