Triple
T10107538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1944 United States Senate election in Connecticut |
E216358
|
entity |
| Predicate | officeTermEndForWinner |
P89926
|
FINISHED |
| Object | January 3, 1951 |
—
|
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 3, 1951 | Statement: [1944 United States Senate election in Connecticut, officeTermEndForWinner, January 3, 1951]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeTermEndForWinner Context triple: [1944 United States Senate election in Connecticut, officeTermEndForWinner, January 3, 1951]
-
A.
officeTermEndOfWinner
chosen
Indicates the date or point in time when the winning candidate’s term in office concludes.
-
B.
officeAssumedByWinner
Indicates that a particular office or position is taken up or assumed by the winner of an election or contest.
-
C.
termStartOfWinner
Indicates the starting date or point in time of the winner’s term in a given role or position.
-
D.
winnerState
Indicates the state or condition of an entity that has achieved victory or been declared the winner in a given context.
-
E.
lastWinner
Indicates that one entity is the most recent winner in a sequence of competitions, contests, or events involving the other entity.
- 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_69ca83d039f08190b9d10363221c69fb |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd0ca7f7c8190ba7ed37940aa933d |
completed | April 2, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:03 p.m.