Triple
T37595719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pussycat (Once Upon a Time in Hollywood character) |
E935378
|
entity |
| Predicate | ridesInVehicleOf |
P90206
|
FINISHED |
| Object | Cliff Booth |
—
|
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: Cliff Booth | Statement: [Pussycat (Once Upon a Time in Hollywood character), ridesInVehicleOf, Cliff Booth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ridesInVehicleOf Context triple: [Pussycat (Once Upon a Time in Hollywood character), ridesInVehicleOf, Cliff Booth]
-
A.
travelsInVehicle
Indicates that an entity is moving from one place to another while being transported inside or on a vehicle.
-
B.
ridesWith
chosen
Indicates that one entity is traveling together in the same vehicle or conveyance as another entity.
-
C.
ridesAt
Indicates that an entity travels on or is transported by another entity (such as a vehicle, animal, or ride) at a given time or context.
-
D.
occursInVehicle
Indicates that an event or action takes place within or on a vehicle.
-
E.
livesInVehicle
Indicates that an entity resides or habitually stays within a vehicle as its primary place of living or presence.
- 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:18 p.m.