Triple
T14032604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Éric Trappier |
E337629
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Trappier |
E1075005
|
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: Trappier | Statement: [Éric Trappier, familyName, Trappier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trappier Context triple: [Éric Trappier, familyName, Trappier]
-
A.
Trappier
chosen
Trappier is a French surname most notably associated with Éric Trappier, the CEO of Dassault Aviation.
-
B.
Trapp
Trapp is a small village in Carmarthenshire, Wales, situated near the historic Carreg Cennen Castle.
-
C.
Troulos
Troulos is a small coastal village and popular beach resort on the Greek island of Skiathos in the Sporades.
-
D.
Trockel
Trockel is the surname of Rosemarie Trockel, a prominent German conceptual artist known for her innovative textile and multimedia works.
-
E.
Schleprock
Schleprock is a perpetually gloomy, bad-luck-bringing character from the Flintstones universe, best known for his catchphrase “Wowzie wow wow.”
- 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_69d81c6543a48190bd5ba93d7419e797 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2fab17008190981f1808726fa11c |
completed | April 14, 2026, 12:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb657ab348190ab51ec0e8caa2c4f |
completed | May 7, 2026, 3:57 p.m. |
Created at: April 9, 2026, 10:20 p.m.