Triple
T21752142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schueller family |
E536940
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Eugène Schueller |
—
|
NE NERFINISHED |
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: Eugène Schueller | Statement: [Schueller family, hasMember, Eugène Schueller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eugène Schueller Context triple: [Schueller family, hasMember, Eugène Schueller]
-
A.
Eugène Schueller
chosen
Eugène Schueller was a French chemist and entrepreneur best known as the founder of the global cosmetics company L'Oréal.
-
B.
Alphonse Lhoest
Alphonse Lhoest was a Belgian colonial officer and naturalist after whom L'Hoest's monkey, a Central African primate species, is named.
-
C.
Leo Baekeland
Leo Baekeland was a Belgian-American chemist and inventor best known for creating Bakelite, the first fully synthetic plastic, which revolutionized the plastics industry.
-
D.
Pierre Gillette
Pierre Gillette is an editor known for his work on the film "Le Soupirant."
-
E.
Wallace Wooley
Wallace Wooley is the mild-mannered, politically ambitious New England politician who becomes entangled with a mischievous witch in the classic 1942 romantic fantasy film "I Married a Witch."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c46eab808190b848242d63a17c47 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01d8a6d4881908cc69e7247cce3a5 |
completed | April 28, 2026, 2:38 a.m. |
Created at: April 16, 2026, 6:50 p.m.