Triple
T5855272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kamala Harris |
E130134
|
entity |
| Predicate | endTimeAsDistrictAttorneyOfSanFrancisco |
P67511
|
FINISHED |
| Object | 2011-01-03 |
—
|
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: 2011-01-03 | Statement: [Kamala Harris, endTimeAsDistrictAttorneyOfSanFrancisco, 2011-01-03]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endTimeAsDistrictAttorneyOfSanFrancisco Context triple: [Kamala Harris, endTimeAsDistrictAttorneyOfSanFrancisco, 2011-01-03]
-
A.
endTime (as Attorney General)
Indicates the point in time when an entity’s role or tenure as Attorney General concludes.
-
B.
endTimeForPosition:Director of Public Prosecutions
Indicates the point in time at which an individual’s tenure in the position of Director of Public Prosecutions concludes.
-
C.
endTime (U.S. Attorney, D.N.J.)
Indicates the time at which the U.S. Attorney’s term of service in the District of New Jersey concluded.
-
D.
termStartAsAttorneyGeneralOfCalifornia
Indicates the date or point in time when an individual began serving as the Attorney General of California.
-
E.
endTimeAsJusticeSecretary
Indicates the point in time at which an individual’s tenure or service as Justice Secretary concludes.
- F. None of above. chosen
Provenance (4 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_69c0084de39081909eb34e6bed74215a |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c044ab0a048190b84be40fb13c0f50 |
completed | March 22, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69c03345ca0c819081c81148d054fed2 |
completed | March 22, 2026, 6:21 p.m. |
| PDg | Predicate description generation | batch_69c044a9c4f0819081b8c196932883f6 |
completed | March 22, 2026, 7:36 p.m. |
Created at: March 22, 2026, 3:55 p.m.