Triple
T1922265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York City Ballet |
E40148
|
entity |
| Predicate | notableChoreographer |
P11856
|
FINISHED |
| Object | Peter Martins |
E202899
|
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: Peter Martins | Statement: [New York City Ballet, notableChoreographer, Peter Martins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Martins Context triple: [New York City Ballet, notableChoreographer, Peter Martins]
-
A.
Peter Martins
chosen
Peter Martins is a Danish ballet dancer and choreographer best known for his long tenure as ballet master in chief of the New York City Ballet.
-
B.
William Forsythe
William Forsythe is an American character actor known for his intense, often villainous roles in action and crime films and television series.
-
C.
Sascha Spoun
Sascha Spoun is a German academic and university administrator who serves as the rector of Leibniz University Hannover.
-
D.
Peter Diener
Peter Diener is a mountaineer best known for being part of the team that made the first successful ascent of Dhaulagiri, one of the world’s highest peaks.
-
E.
Peter Ott
Peter Ott was an Austrian general who played a significant command role in the Napoleonic Wars, notably during the Italian campaigns.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a8864298748190a2f2fd34f7ef8d77 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb233011881908736523d36f01b0c |
completed | March 7, 2026, 5:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adf3e458e8819098ea1c2d5598f890 |
completed | March 8, 2026, 10:10 p.m. |
Created at: March 4, 2026, 7:35 p.m.