Triple
T28274547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Above Suspicion |
E712951
|
entity |
| Predicate | policeRankOfProtagonist |
P47215
|
FINISHED |
| Object | detective constable |
—
|
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: detective constable | Statement: [Above Suspicion, policeRankOfProtagonist, detective constable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policeRankOfProtagonist Context triple: [Above Suspicion, policeRankOfProtagonist, detective constable]
-
A.
policeRank
chosen
Indicates that one entity holds a specific rank or position within a police organization relative to another entity.
-
B.
policeCharacter
Indicates that one entity serves as a police officer or law-enforcement figure in relation to another entity.
-
C.
isHighestRankedUniformedOfficerIn
Indicates that one entity holds the top-ranking position among all uniformed officers within a specified organization or jurisdiction.
-
D.
hasPoliceRole
Indicates that an entity holds or performs a specific role, duty, or function within a police or law enforcement context.
-
E.
officerCategory
Indicates the classification or type of officer role that an individual holds within an organization or system.
- 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_69efb52275788190ae5181ccebef18ce |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f68805b4848190b75da14996d52a38 |
completed | May 2, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f68609c0b08190a8e1238a4d97c270 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 27, 2026, 11:19 p.m.