Triple
T266876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VPOTUS |
E5748
|
entity |
| Predicate | currentOfficeHolderStartDate |
P1814
|
FINISHED |
| Object | January 20, 2021 |
—
|
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: January 20, 2021 | Statement: [VPOTUS, currentOfficeHolderStartDate, January 20, 2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentOfficeHolderStartDate Context triple: [VPOTUS, currentOfficeHolderStartDate, January 20, 2021]
-
A.
officeHolderStartTime
chosen
Indicates the date and time at which an individual begins holding a particular office or position.
-
B.
inauguralHolderStartDate
Indicates the date on which the first person or entity to hold a position, title, or role officially began their tenure.
-
C.
currentChairStartDate
Indicates the date on which the person’s current term as chair officially began.
-
D.
officeholderEndTime
Indicates the time or date at which a person’s term in a particular office or position comes to an end.
-
E.
firstOfficeHolder
Indicates that the subject is the very first individual to hold a particular office or position associated with the object.
- 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_69a2587daeb081909591b9d30f80a271 |
completed | Feb. 28, 2026, 2:52 a.m. |
| NER | Named-entity recognition | batch_69a25dacf60c8190a5c3ef455b9a8b20 |
completed | Feb. 28, 2026, 3:14 a.m. |
| PD | Predicate disambiguation | batch_69a25b6f60b081908fc6467800a8849e |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:56 a.m.