Triple
T1186524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pulitzer Prize for Feature Photography |
E25259
|
entity |
| Predicate | hasAwardedForWorkPublishedIn |
P8623
|
FINISHED |
| Object | print newspapers |
—
|
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: print newspapers | Statement: [Pulitzer Prize for Feature Photography, hasAwardedForWorkPublishedIn, print newspapers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAwardedForWorkPublishedIn Context triple: [Pulitzer Prize for Feature Photography, hasAwardedForWorkPublishedIn, print newspapers]
-
A.
awardReceivedByWork
Indicates that a particular award was given in recognition of a specific work (such as a book, film, or artwork).
-
B.
hasPublication
Indicates that an entity is associated with or responsible for a specific publication.
-
C.
hasAwarded
Indicates that one entity has given or conferred an award to another entity.
-
D.
notableAwardWork
Indicates that a work is the specific creation (e.g., book, film, artwork) for which an award or honor was given.
-
E.
hasAwardedWorkType
chosen
Indicates that an entity has granted or is associated with a specific type or category of work that has received an award.
- 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_69a49427d98881908646d6c63b8cea1e |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd5578b08190bbe4089857fbf166 |
completed | March 1, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69a4bb59ca6c81908597a81646674aaa |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.