Triple
T2340853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eric Holder |
E45021
|
entity |
| Predicate | officeStartTime (United States Attorney General) |
P31762
|
FINISHED |
| Object | 2009-02-03 |
—
|
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: 2009-02-03 | Statement: [Eric Holder, officeStartTime (United States Attorney General), 2009-02-03]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeStartTime (United States Attorney General) Context triple: [Eric Holder, officeStartTime (United States Attorney General), 2009-02-03]
-
A.
startTime (as Attorney General)
chosen
Indicates the date and time at which an individual began serving in the role of Attorney General.
-
B.
officeStartTime (Governor of Tennessee)
Indicates the time at which the Governor of Tennessee officially begins their term in office.
-
C.
officeStartAfter
Indicates that one entity’s term or period in office begins after another specified time or event.
-
D.
startTimeAsSolicitorGeneral
Indicates the point in time when an individual began serving in the role of Solicitor General.
-
E.
startTime (U.S. Attorney, D.N.J.)
Indicates the time at which the U.S. Attorney for the District of New Jersey begins their term or officially assumes office.
- 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_69a88917935081909b755dbf38e81024 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abcade3c808190ab3803538ccbe620 |
completed | March 7, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69abc59616a8819099711834e6f1ccd6 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:52 p.m.