Triple
T536978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Cuomo |
E12346
|
entity |
| Predicate | startTime (spouse Kerry Kennedy) |
P14428
|
FINISHED |
| Object | 1990 |
—
|
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: 1990 | Statement: [Andrew Cuomo, startTime (spouse Kerry Kennedy), 1990]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTime (spouse Kerry Kennedy) Context triple: [Andrew Cuomo, startTime (spouse Kerry Kennedy), 1990]
-
A.
spouseStartTime
chosen
Indicates the point in time when two individuals began their spousal (marriage) relationship.
-
B.
startTimeOfPosition_WhiteHouseChiefOfStaff
Indicates the point in time when an individual begins serving in the role of White House Chief of Staff.
-
C.
endTimeOfPosition_WhiteHouseChiefOfStaff
Indicates the time at which an individual's tenure in the role of White House Chief of Staff ends.
-
D.
servedAsFirstLadyOfTheUnitedStatesFrom
Indicates that a person held the role of First Lady of the United States during a specified time period.
-
E.
precededAsFirstLadyOfTheUnitedStatesBy
Indicates that one person served as First Lady of the United States immediately before another person.
- 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_69a4933208e88190891f5debab1b776d |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4985e51908190a34aa82ea9dbee1e |
completed | March 1, 2026, 7:49 p.m. |
| PD | Predicate disambiguation | batch_69a494b51ff08190a39f4168fd9a7ddf |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.