Triple
T25288057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Judy Agnew |
E633999
|
entity |
| Predicate | secondLadyDuring |
P169887
|
FINISHED |
| Object | Nixon administration |
—
|
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: Nixon administration | Statement: [Judy Agnew, secondLadyDuring, Nixon administration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondLadyDuring Context triple: [Judy Agnew, secondLadyDuring, Nixon administration]
-
A.
secondLadyTo
Indicates that one person holds the position or role of second lady in relation to another person or office.
-
B.
precededInSecondLadyRoleBy
Indicates that one person held the role of Second Lady immediately before another person, establishing a direct predecessor relationship in that position.
-
C.
successorAsSecondLady
Indicates that one person became the next Second Lady, directly following another in that role.
-
D.
predecessorAsSecondLady
Indicates that one person held the position of Second Lady of a country immediately before another person.
-
E.
attendingIncomingSecondLady
Indicates that an individual is present at and participating in an event in the capacity of the incoming Second Lady.
- 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_69e75a9402fc81909362ca85277c06d9 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f688d015908190ad5df37030ecf332 |
completed | May 2, 2026, 11:29 p.m. |
| PD | Predicate disambiguation | batch_69f68609c0b08190a8e1238a4d97c270 |
completed | May 2, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69f688034580819086a0f9100645f8ba |
completed | May 2, 2026, 11:25 p.m. |
Created at: April 21, 2026, 1:19 p.m.