Triple
T21505370
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dia Art Foundation |
E530583
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Helen Winkler |
—
|
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: Helen Winkler | Statement: [Dia Art Foundation, foundedBy, Helen Winkler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helen Winkler Context triple: [Dia Art Foundation, foundedBy, Helen Winkler]
-
A.
Helen Winkler
chosen
Helen Winkler is an arts patron and founder of the Dia Art Foundation, known for supporting ambitious, long-term projects by contemporary artists.
-
B.
Helen Schonberger
Helen Schonberger was the wife of comedian Moe Howard of The Three Stooges.
-
C.
Mary Winternitz
Mary Winternitz was the wife of American novelist and short story writer John Cheever.
-
D.
Helen Winner
Helen Winner was the mother of British film director and producer Michael Winner.
-
E.
Paula Winkler
Paula Winkler was a German-Jewish writer and intellectual who collaborated closely with her husband, the philosopher and theologian Martin Buber.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c45c81f08190a6b8bbb70a45aae7 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea7cb5588190a4473bbfe3f49cbb |
completed | April 23, 2026, 9:46 a.m. |
Created at: April 16, 2026, 6:24 p.m.