Triple
T1174914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Best Direction of a Play |
E25000
|
entity |
| Predicate | hasAwardCriteria |
P216
|
FINISHED |
| Object | outstanding achievement in directing a play on Broadway |
—
|
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: outstanding achievement in directing a play on Broadway | Statement: [Best Direction of a Play, hasAwardCriteria, outstanding achievement in directing a play on Broadway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAwardCriteria Context triple: [Best Direction of a Play, hasAwardCriteria, outstanding achievement in directing a play on Broadway]
-
A.
awardCriteria
chosen
Indicates the standards or conditions used to determine eligibility for receiving an award or recognition.
-
B.
hasAwardLevel
Indicates that an entity possesses or has been assigned a specific level, tier, or rank within an award or recognition system.
-
C.
canAward
Indicates that one entity has the authority or ability to grant an award, honor, or recognition to another entity.
-
D.
hasAwarded
Indicates that one entity has given or conferred an award to another entity.
-
E.
canBeAwardedTo
Indicates that something is eligible to receive or be granted a particular award, honor, or recognition.
- 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_69a494267b4c819088c97a59182bf56a |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd53e4b48190abb2167f8074a6bc |
completed | March 1, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5844348190b01ac6506906ba3b |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.