Triple
T31803088
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marshal Micah Torrance |
E811793
|
entity |
| Predicate | isLawmanIn |
P10531
|
FINISHED |
| Object | North Fork |
—
|
NE NERFINISHED |
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: North Fork | Statement: [Marshal Micah Torrance, isLawmanIn, North Fork]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLawmanIn Context triple: [Marshal Micah Torrance, isLawmanIn, North Fork]
-
A.
isLawEnforcement
Indicates that an entity serves in an official capacity to enforce laws, maintain public order, and uphold legal regulations.
-
B.
isSwornOfficer
Indicates that an individual holds official law enforcement authority through a formal oath of office.
-
C.
hasUnitedStatesMarshal
Indicates that an entity is associated with or served by a particular United States Marshal.
-
D.
areOfficialIn
chosen
Indicates that an entity holds an official role, position, or capacity within another entity (such as an organization, institution, or jurisdiction).
-
E.
enforcesLawThrough
Indicates that one entity upholds, applies, or executes laws or legal rules by means of another entity, mechanism, or process.
- 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_69f348e70d188190b4637c5509f81274 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:42 p.m.