Triple
T33177830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maxine Carroll |
E849231
|
entity |
| Predicate | relationshipToMayor |
P193741
|
FINISHED |
| Object | secretary |
—
|
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: secretary | Statement: [Maxine Carroll, relationshipToMayor, secretary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToMayor Context triple: [Maxine Carroll, relationshipToMayor, secretary]
-
A.
relationshipToGovernor
Indicates the specific familial, professional, or social relationship that one entity has to a governor.
-
B.
relationToCouncil
Indicates the nature or type of connection an entity has with a council, such as membership, oversight, affiliation, or governance relationship.
-
C.
cityMayor
Indicates that one entity serves as the mayor (chief elected municipal official) of the city represented by the other entity.
-
D.
underMayor
chosen
Indicates that one entity holds a position, role, or responsibility that is subordinate to or overseen by a mayor.
-
E.
relationshipToParliament
Indicates the nature or type of formal connection an entity has with a parliament, such as its role, status, or institutional relationship to that legislative body.
- 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_69f3495d06508190b0b7729982982cea |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f338b881908e5593e45d764f4d |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:29 a.m.