Triple
T32173864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hard Boiled |
E821782
|
entity |
| Predicate | directorSignatureWorkOf |
P491
|
FINISHED |
| Object | John Woo |
—
|
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: John Woo | Statement: [Hard Boiled, directorSignatureWorkOf, John Woo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directorSignatureWorkOf Context triple: [Hard Boiled, directorSignatureWorkOf, John Woo]
-
A.
signatureWork
chosen
Indicates that the work is a defining or most representative creation associated with an entity (such as a person, group, or organization).
-
B.
signatureWorkType
Indicates the specific category or type of work that serves as a defining or primary example associated with an entity.
-
C.
signatureWorkSeries
Indicates that a work is part of a designated "signature" series or collection associated with a creator, brand, or entity.
-
D.
signedArtist
Indicates that an artist has entered into a formal contract or agreement with a label, company, or representative.
-
E.
signedByArtist
Indicates that an item, such as a work or object, bears the authentic signature of the specified artist.
- 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_69f3490699a48190bbef96b198e8fade |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd3d46d1f48190a1b20dd063224b7d |
completed | May 8, 2026, 1:32 a.m. |
| PD | Predicate disambiguation | batch_69fd3ae1510c81908fe1280efc17feee |
completed | May 8, 2026, 1:22 a.m. |
Created at: May 1, 2026, 12:34 a.m.