Triple
T21263062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johnny Hooker |
E524052
|
entity |
| Predicate | hasPartnerInCrime |
P21638
|
FINISHED |
| Object | Henry Gondorff |
—
|
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: Henry Gondorff | Statement: [Johnny Hooker, hasPartnerInCrime, Henry Gondorff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPartnerInCrime Context triple: [Johnny Hooker, hasPartnerInCrime, Henry Gondorff]
-
A.
partnerInCrime
chosen
Indicates a relationship where two or more entities collaborate closely in committing or planning wrongful, illicit, or mischievous acts together.
-
B.
hasCrimeGroup
Indicates a relationship where an entity is associated with, belongs to, or is controlled by a particular criminal group or organization.
-
C.
hasCriminalCharacter
Indicates that an entity possesses traits, behaviors, or a reputation associated with criminal activity or unlawful conduct.
-
D.
hasPartInMurderOf
Indicates involvement as a contributing participant in the commission of a murder.
-
E.
hasPolicePartner
Indicates that one entity has another entity as its partner in a police or law-enforcement context.
- 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_69e0b5156d7881909bd4f83676590715 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735e9b2788190b834ba38367fb6c7 |
completed | April 21, 2026, 8:31 a.m. |
| PD | Predicate disambiguation | batch_69e5f61239708190ab7b3c83ae848a0d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 4 p.m.