Triple
T16314696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nice metropolitan area |
E396143
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Drap |
E583515
|
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: Drap | Statement: [Nice metropolitan area, contains, Drap]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drap Context triple: [Nice metropolitan area, contains, Drap]
-
A.
Drap
chosen
Drap is a small commune in the Alpes-Maritimes department of southeastern France, situated near Nice on the French Riviera.
-
B.
Tailo
Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
-
C.
Clapet
Clapet is the sinister butcher and landlord who serves as the main antagonist in the darkly comic French film "Delicatessen."
-
D.
Cappa
Cappa is the nickname of Darryl Hill, an individual known primarily under this alias.
-
E.
Cappa
Cappa is the stage name and common nickname of Cappadonna, an American rapper closely associated with the Wu-Tang Clan.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e288de57cc81908cec93309347c385 |
completed | April 17, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001fa88e8c8190b0423b60389896dc |
completed | May 10, 2026, 6:03 a.m. |
Created at: April 10, 2026, 5:06 a.m.