Triple
T2659210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billy Costigan |
E54685
|
entity |
| Predicate | undercoverRole |
P3707
|
FINISHED |
| Object | member of Frank Costello's crew |
—
|
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: member of Frank Costello's crew | Statement: [Billy Costigan, undercoverRole, member of Frank Costello's crew]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: undercoverRole Context triple: [Billy Costigan, undercoverRole, member of Frank Costello's crew]
-
A.
disguisedAs
Indicates that one entity is intentionally presenting itself as, or made to appear as, another entity in order to conceal its true identity.
-
B.
usesMasksOrDisguises
Indicates that an entity employs masks, costumes, or other forms of disguise to conceal or alter its identity in the context of an action or interaction.
-
C.
deFactoRole
chosen
Indicates that an entity effectively functions in a role or capacity in practice, even if that role is not formally or officially assigned.
-
D.
roleInScene
Indicates that an entity participates in a particular scene with a specific role or function within that scene.
-
E.
roleInOperationJustCause
Indicates that an entity participated in or held a specific role during Operation Just Cause.
- 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_69ab49e028948190b97e01d73548b1d9 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd94dcaa48190aec625f68ce61a02 |
completed | March 7, 2026, 7:52 a.m. |
| PD | Predicate disambiguation | batch_69abd81768748190bd965f367cf6ef37 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:53 p.m.