Triple
T26444009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr. Cab Driver |
E665162
|
entity |
| Predicate | releaseYearApproximate |
P49730
|
FINISHED |
| Object | 1989 |
—
|
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: 1989 | Statement: [Mr. Cab Driver, releaseYearApproximate, 1989]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: releaseYearApproximate Context triple: [Mr. Cab Driver, releaseYearApproximate, 1989]
-
A.
releaseApproximateYear
chosen
Indicates that an entity was released or made available around a specified year, where the year is approximate rather than exact.
-
B.
retitleApproxYear
Indicates that an entity was retitled or renamed around an approximate year, rather than at a precisely known date.
-
C.
approximatePremiereYear
Indicates the estimated calendar year in which something, typically a work or event, first premiered.
-
D.
endYearApprox
Indicates that the end year of an event, state, or relationship is known only approximately rather than as a precise calendar year.
-
E.
approximateYearWritten
Indicates the estimated calendar year in which something was written, when the exact year is not known.
- 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_69ee883c851881909e2ab04efbb3c5fe |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f65aa07c048190a5df30d53d8f0cf5 |
completed | May 2, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f659cc571c819097e51e531961d812 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 27, 2026, midnight