Triple
T35709309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pantomimes lumineuses |
E1031808
|
entity |
| Predicate | firstPublicPresentationPlace |
P138066
|
FINISHED |
| Object | Musée Grévin, Paris |
E1031811
|
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: Musée Grévin, Paris | Statement: [Pantomimes lumineuses, firstPublicPresentationPlace, Musée Grévin, Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPublicPresentationPlace Context triple: [Pantomimes lumineuses, firstPublicPresentationPlace, Musée Grévin, Paris]
-
A.
firstPublicReadingPlace
Indicates the location where a work, text, or piece was first publicly read or performed before an audience.
-
B.
firstPerformanceLocationOfWorkAppearingIn
chosen
Indicates the location where a work was first performed or premiered.
-
C.
placeOfFirstPublication
Indicates the location where a work was first published or made publicly available.
-
D.
firstExhibited
Indicates the event or context in which something was publicly displayed or presented for the first time.
-
E.
firstUSPerformanceLocation
Indicates the location where an entity was first performed in the United States.
- F. None of above.
Provenance (4 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_69f76e0df1d08190965b1c6dff94c391 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a3885e79e788190add7887e2fefb7c7 |
completed | June 22, 2026, 12:46 a.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:05 p.m.