Triple
T20048634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Laure Junot, Duchess of Abrantès |
E499131
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Laure |
—
|
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: Laure | Statement: [Laure Junot, Duchess of Abrantès, givenName, Laure]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laure Context triple: [Laure Junot, Duchess of Abrantès, givenName, Laure]
-
A.
Laure
chosen
Laure is a feminine given name, primarily used in French-speaking countries, that is a variant of the name Laura.
-
B.
Laureline
Laureline is a courageous and quick-witted space-time agent who partners with Valerian in the sci-fi universe of "Valerian and the City of a Thousand Planets."
-
C.
Delannay
Delannay is a variant spelling of the surname Delannoy, which is of French origin.
-
D.
Leandre
Leandre is a French given name, cognate with Leander, traditionally associated with romantic and classical literary figures.
-
E.
Lère
Lère is a small river in southern France that serves as a tributary of the Aveyron River.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6632c085081908710cbc939ac9971 |
completed | April 20, 2026, 5:32 p.m. |
Created at: April 11, 2026, 3:37 p.m.