Triple
T30263420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irja Pullman |
E769564
|
entity |
| Predicate | spouseOfNobelLaureateInChemistry |
P68945
|
FINISHED |
| Object | Robert Burns Woodward |
—
|
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: Robert Burns Woodward | Statement: [Irja Pullman, spouseOfNobelLaureateInChemistry, Robert Burns Woodward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseOfNobelLaureateInChemistry Context triple: [Irja Pullman, spouseOfNobelLaureateInChemistry, Robert Burns Woodward]
-
A.
spouseOfNobelLaureateIn
chosen
Indicates that one entity is the spouse of a Nobel Prize laureate associated with a specified field, category, or year.
-
B.
spouseNobelPrizeYear
Indicates the year in which the spouse of the referenced person received a Nobel Prize.
-
C.
associatedNobelPrizeInChemistryYear
Indicates the year in which the related entity received or is linked to a Nobel Prize in Chemistry.
-
D.
spouseNobelPrizeCountry
Indicates that the country referenced is associated with the Nobel Prize received by the spouse of the given person.
-
E.
spouseOfPulitzerPrizeWinner
Indicates being the spouse of a person who has won a Pulitzer Prize.
- 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_69f22484a5f48190b678cd607700bc82 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: April 29, 2026, 7:42 p.m.