Triple
T71973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kimberly Guilfoyle |
E1439
|
entity |
| Predicate | hasProfession |
P2374
|
FINISHED |
| Object | prosecutor |
—
|
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: prosecutor | Statement: [Kimberly Guilfoyle, hasProfession, prosecutor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProfession Context triple: [Kimberly Guilfoyle, hasProfession, prosecutor]
-
A.
subjectOccupation
chosen
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
-
B.
authorOccupation
Indicates the professional role or job that an author holds or is associated with.
-
C.
hadOccupationStatusUntil
Indicates that an entity held a particular occupational status up to, but not necessarily beyond, a specified point in time.
-
D.
namesakeOccupation
Indicates that one entity’s occupation is the same as, or derived from, the occupation associated with the other entity’s namesake.
-
E.
hasEconomicRole
Indicates that an entity participates in or fulfills a specific function, position, or responsibility within an economic system or activity.
- 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_69a24c06b3bc8190aa4ac89026115efc |
completed | Feb. 28, 2026, 1:59 a.m. |
| NER | Named-entity recognition | batch_69a24f6997c081908b202f937eb2b14f |
completed | Feb. 28, 2026, 2:14 a.m. |
| PD | Predicate disambiguation | batch_69a24eab7f408190a8275cb82474f575 |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:03 a.m.