Triple
T38550497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Earl Spilner |
E925096
|
entity |
| Predicate | occupationUnderCover |
P140052
|
FINISHED |
| Object | police officer |
—
|
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: police officer | Statement: [Brian Earl Spilner, occupationUnderCover, police officer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occupationUnderCover Context triple: [Brian Earl Spilner, occupationUnderCover, police officer]
-
A.
undercoverIn
Indicates that an entity is secretly operating within a group, organization, or environment under false or concealed identity.
-
B.
undercoverFor
Indicates that one entity is secretly acting on behalf of or within another entity, typically to gather information or carry out covert objectives without revealing their true affiliation.
-
C.
undercoverAgainst
Indicates that one entity is secretly acting in a covert or deceptive capacity directed against another entity.
-
D.
resultOfUndercoverWork
Indicates that something occurs as a consequence of, or is produced by, undercover investigative work.
-
E.
occupationInDisguise
chosen
Indicates that an entity’s true occupation is being concealed or performed under a false or hidden identity.
- 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_69f76eaeb69c8190b367df9330d6f6af |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcd3163d0881909d3209cd7cb81c10 |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f81cbc8190b4fd3bfc3106c1f3 |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.