Triple
T36985996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Connecticut for Lieberman |
E914963
|
entity |
| Predicate | createdToSupportCandidacyOf |
P201087
|
FINISHED |
| Object | Joe Lieberman |
—
|
NE NERFINISHED |
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: Joe Lieberman | Statement: [Connecticut for Lieberman, createdToSupportCandidacyOf, Joe Lieberman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdToSupportCandidacyOf Context triple: [Connecticut for Lieberman, createdToSupportCandidacyOf, Joe Lieberman]
-
A.
allowsCandidacyTo
Indicates that one entity grants another entity the right or eligibility to stand as a candidate for a position, role, or office.
-
B.
candidacyEvent
Indicates an event in which an entity formally becomes or is recognized as a candidate for a position, role, or office.
-
C.
candidacyStartDate
Indicates the date on which an entity’s candidacy for a role, position, or election officially begins.
-
D.
wasCandidateIn
Indicates that an entity served as a candidate in a particular election, contest, or selection process.
-
E.
announcedCandidacyFor
Indicates that an entity has publicly declared their intention to run as a candidate for a specific position, office, or role.
- 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_69f76e8dd0408190b8b46da118ea5128 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffc704e1e88190884928a6a5c55a87 |
completed | May 9, 2026, 11:45 p.m. |
| PD | Predicate disambiguation | batch_69ffc6b483d881908ad872e25fa6abc5 |
completed | May 9, 2026, 11:43 p.m. |
| PDg | Predicate description generation | batch_69ffc70423f08190bd7c0625b21147a4 |
completed | May 9, 2026, 11:45 p.m. |
Created at: May 3, 2026, 4:14 p.m.