Triple
T38259999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Hudsonian Curlew |
E1017901
|
entity |
| Predicate | partOfPulitzerPrizeWinningWork |
P131077
|
FINISHED |
| Object | Turtle Island |
E326546
|
NE 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: Turtle Island | Statement: [The Hudsonian Curlew, partOfPulitzerPrizeWinningWork, Turtle Island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfPulitzerPrizeWinningWork Context triple: [The Hudsonian Curlew, partOfPulitzerPrizeWinningWork, Turtle Island]
-
A.
hasPartInWrittenWork
Indicates that an entity participates in or contributes to the creation of a written work.
-
B.
adaptationOfPulitzerPrizeWinningWork
Indicates that the subject is an adaptation of a work that has received a Pulitzer Prize.
-
C.
sharesPulitzerPrizeWith
Indicates that two entities are co-recipients of the same Pulitzer Prize award.
-
D.
hasPartInCreativeOutput
Indicates that an entity contributed a component, role, or involvement to the creation or production of a particular creative work.
-
E.
isPartOfBodyOfWork
chosen
Indicates that one creative work is a component, segment, or installment within a larger overarching body of related work.
- F. None of above.
Provenance (4 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_69f76de33e4481909099fa812709bd42 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a01b241f7308190bedb7522cb5dc069 |
completed | May 11, 2026, 10:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41e010a4d0819088157e99d4a72d5c |
completed | June 29, 2026, 3:01 a.m. |
| PD | Predicate disambiguation | batch_6a01b19ff12c81908ee1b188b4a3e118 |
completed | May 11, 2026, 10:38 a.m. |
Created at: May 3, 2026, 4:30 p.m.