Triple
T17602618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rohan-Soubise branch |
E428740
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Soubise |
—
|
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: Soubise | Statement: [Rohan-Soubise branch, namedAfter, Soubise]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soubise Context triple: [Rohan-Soubise branch, namedAfter, Soubise]
-
A.
Soubise
chosen
Soubise is a historic French seigneurial domain and title, most notably linked to the noble House of Rohan and the princes who bore its name.
-
B.
Bouchercon
Bouchercon is an annual convention dedicated to mystery and crime fiction that brings together authors, fans, and industry professionals for panels, awards, and related events.
-
C.
La Provençale
La Provençale is the section of France’s A8 motorway that runs across Provence, linking cities such as Aix-en-Provence, Cannes, and Nice along the Mediterranean coast.
-
D.
Commenailles
Commenailles is a small rural commune in the Jura department of eastern France, known for its agricultural landscape within the Bourgogne-Franche-Comté region.
-
E.
Bouchoir
Bouchoir is a small French commune located in the Somme department in northern France.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c49dbe081909bd39879c70fe27c |
completed | April 19, 2026, 5:46 a.m. |
Created at: April 10, 2026, 5:51 a.m.