Triple
T1105609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ang Lee |
E25480
|
entity |
| Predicate | wonForWork |
P15276
|
FINISHED |
| Object | Academy Award for Best Director for Brokeback Mountain |
—
|
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: Academy Award for Best Director for Brokeback Mountain | Statement: [Ang Lee, wonForWork, Academy Award for Best Director for Brokeback Mountain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonForWork Context triple: [Ang Lee, wonForWork, Academy Award for Best Director for Brokeback Mountain]
-
A.
wonFor
chosen
Indicates that one entity received an award, prize, or recognition specifically on behalf of or representing another entity.
-
B.
workBecame
Indicates that one work was transformed, adapted, or evolved into another work over time.
-
C.
workBy
Indicates that a work (such as a creation, product, or result) is produced, authored, or created by a particular agent or entity.
-
D.
eligibleWork
Indicates that a particular work satisfies the necessary conditions or criteria to qualify for a specified status, benefit, or consideration.
-
E.
eligibleWorks
Indicates that certain works meet the required criteria or conditions to qualify for a specified status, use, or consideration.
- 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e21f048190bf4b63dd2c7c7641 |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b74877748190b78cd8847ee4fa7a |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:43 p.m.