Triple
T3525997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yeovil |
E74538
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Herblay-sur-Seine |
E258290
|
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: Herblay-sur-Seine | Statement: [Yeovil, hasTwinTown, Herblay-sur-Seine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herblay-sur-Seine Context triple: [Yeovil, hasTwinTown, Herblay-sur-Seine]
-
A.
Herblay-sur-Seine
chosen
Herblay-sur-Seine is a suburban commune in the northwestern outskirts of Paris, France, situated along the Seine River.
-
B.
Vulaines-sur-Seine
Vulaines-sur-Seine is a small commune in north-central France, known in part as the place where the symbolist poet Stéphane Mallarmé died.
-
C.
Champs-sur-Marne
Champs-sur-Marne is a suburban commune in the eastern outskirts of Paris, France, known for its historic château and role as a hub for higher education and research institutions.
-
D.
Précy-sur-Marne
Précy-sur-Marne is a small French commune in the Seine-et-Marne department in the Île-de-France region, situated along the Marne River east of Paris.
-
E.
Ablon-sur-Seine
Ablon-sur-Seine is a small suburban commune in the southeastern outskirts of Paris, France, situated along the Seine River in the Val-de-Marne department.
- 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_69ad85d0c5488190a3d8e02ebd01a1aa |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbc6a8d0c819094d38b9c47fb67b4 |
completed | March 8, 2026, 6:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b37e8de2648190809369c3f0b7d85d |
completed | March 13, 2026, 3:03 a.m. |
Created at: March 8, 2026, 3:19 p.m.