Triple
T2854675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Cousine Bette |
E63171
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object | Crevel |
E306673
|
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: Crevel | Statement: [La Cousine Bette, hasCharacter, Crevel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crevel Context triple: [La Cousine Bette, hasCharacter, Crevel]
-
A.
Crevel
chosen
Crevel is a vain, wealthy former perfumer and libertine in Honoré de Balzac’s novel "La Cousine Bette," emblematic of the corrupt bourgeois society he satirizes.
-
B.
Casteau
Casteau is a village in Belgium best known as the site of NATO’s Supreme Headquarters Allied Powers Europe (SHAPE).
-
C.
Vesoul
Vesoul is a commune in eastern France that serves as the administrative center (prefecture) of the Haute-Saône department.
-
D.
Cité
Cité is a Paris Métro station located on the Île de la Cité in the historic center of Paris.
-
E.
Saint-Preux
Saint-Preux is the sensitive, idealistic tutor and lover in Jean-Jacques Rousseau’s epistolary novel "Julie, or the New Heloise," embodying Enlightenment-era conflicts between passion, virtue, and social convention.
- 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_69ab4c407c408190857d25e027155ce9 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdf60852c8190b66c8719c63a723e |
completed | March 7, 2026, 8:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b055e0c8088190a0fa67c9c14fc29b |
completed | March 10, 2026, 5:33 p.m. |
Created at: March 6, 2026, 10:02 p.m.