Triple
T22071817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | P.C. Hooft Prize |
E545425
|
entity |
| Predicate | notableRecipient |
P108
|
FINISHED |
| Object | Judith Herzberg |
—
|
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: Judith Herzberg | Statement: [P.C. Hooft Prize, notableRecipient, Judith Herzberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Judith Herzberg Context triple: [P.C. Hooft Prize, notableRecipient, Judith Herzberg]
-
A.
Judith Herzberg
chosen
Judith Herzberg is a Dutch poet, playwright, and essayist renowned for her clear, understated style and influential contributions to contemporary Dutch literature.
-
B.
Judith Feldman
Judith Feldman is a screenwriter best known for her work on the 1997 film "An American Affair."
-
C.
Judith Ehrlich
Judith Ehrlich is an American documentary filmmaker best known for co-directing the Academy Award–nominated film "The Most Dangerous Man in America: Daniel Ellsberg and the Pentagon Papers."
-
D.
Judith Gellman
Judith Gellman is a costume designer best known for her work on the 1995 film adaptation of "A Little Princess."
-
E.
Esther Hornstein
Esther Hornstein is a film producer known for her work on the 2022 movie "The Contractor."
- 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_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12888dcc08190b18d3d44d09ab943 |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:28 p.m.