Triple
T19860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John H. Sununu |
E395
|
entity |
| Predicate | startTimeOfPosition_WhiteHouseChiefOfStaff |
P1811
|
FINISHED |
| Object | 1989 |
—
|
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: 1989 | Statement: [John H. Sununu, startTimeOfPosition_WhiteHouseChiefOfStaff, 1989]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeOfPosition_WhiteHouseChiefOfStaff Context triple: [John H. Sununu, startTimeOfPosition_WhiteHouseChiefOfStaff, 1989]
-
A.
inaugurationDay
Indicates the specific day on which a formal ceremony is held to induct someone into an official position or office.
-
B.
startTimeOfPositionHeld: President of the United States
Indicates the date and time when an individual began serving in the position of President of the United States.
-
C.
endTimeOfPositionHeld: President of the United States
Indicates the date and time when an individual's tenure in the position of President of the United States concludes.
-
D.
firstInOfficeTo
Indicates that one entity was the earliest or first to hold a particular office or position in relation to another entity or context.
-
E.
servedAsPresidentDuring
Indicates that a person held the office of president for the duration of a specified time period or event.
- 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_69a240778d288190815c0052ebbbcc91 |
completed | Feb. 28, 2026, 1:10 a.m. |
| NER | Named-entity recognition | batch_69a24703cb988190ad2bc181d27829e4 |
completed | Feb. 28, 2026, 1:38 a.m. |
| PD | Predicate disambiguation | batch_69a24650f1f0819081e638fafd18d687 |
completed | Feb. 28, 2026, 1:35 a.m. |
| PDg | Predicate description generation | batch_69a24702d4988190a54a4e578b7c919e |
completed | Feb. 28, 2026, 1:38 a.m. |
Created at: Feb. 28, 2026, 1:14 a.m.