Triple
T23604176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heartbeat |
E582844
|
entity |
| Predicate | performerKnownForTelevisionSeries |
P131071
|
FINISHED |
| Object | Miami Vice |
—
|
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: Miami Vice | Statement: [Heartbeat, performerKnownForTelevisionSeries, Miami Vice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performerKnownForTelevisionSeries Context triple: [Heartbeat, performerKnownForTelevisionSeries, Miami Vice]
-
A.
performerOn
Indicates that an entity serves as the performer or executing agent of an action, event, or work associated with another entity.
-
B.
actorKnownFor
chosen
Indicates that an actor is widely recognized or notable for a particular work, role, or contribution.
-
C.
performerCharacterName
Indicates that a performer is associated with or portrays a specific character name in a performance or work.
-
D.
performerCreditedAs
Indicates that a performer is associated with a work under a specific credited name or alias.
-
E.
portrayedByAlsoKnownFor
Indicates that an entity is portrayed by a person who is also notably known for another specific role or work.
- 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_69e248faa2788190abb1581742daa6aa |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b0ee6ce881909f556404cc235418 |
completed | April 29, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69f118c96a0081908a8ac98ef7e7e60c |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:44 p.m.