Triple
T11762067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On Your Feet! |
E279680
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Hal Luftig |
E416734
|
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: Hal Luftig | Statement: [On Your Feet!, producer, Hal Luftig]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hal Luftig Context triple: [On Your Feet!, producer, Hal Luftig]
-
A.
Hal Luftig
chosen
Hal Luftig is a prominent American theatrical producer known for his work on major Broadway shows, including multiple Tony Award–winning productions.
-
B.
Uri Nodelman
Uri Nodelman is a philosopher and academic best known for serving as editor-in-chief of the Stanford Encyclopedia of Philosophy, a leading online reference in the field.
-
C.
M.G. Siegler
M.G. Siegler is a technology writer and venture capitalist known for his work at TechCrunch and his investing role at Google Ventures (GV).
-
D.
Morton Heiligman
Morton Heiligman is an academic known for supervising the doctoral work of computer scientist and Smalltalk pioneer Adele Goldberg.
-
E.
Robert L. May
Robert L. May was an American copywriter and author best known for creating the Christmas character Rudolph the Red-Nosed Reindeer.
- 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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a52386708190b744746a2db37495 |
completed | April 10, 2026, 7:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f01a4be7c481908deab31f2ee20e0c |
completed | April 28, 2026, 2:24 a.m. |
Created at: April 8, 2026, 9:41 p.m.