Triple
T10815441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heunisch Weiss |
E255216
|
entity |
| Predicate | parentOf |
P120
|
FINISHED |
| Object | Romorantin |
E243825
|
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: Romorantin | Statement: [Heunisch Weiss, parentOf, Romorantin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Romorantin Context triple: [Heunisch Weiss, parentOf, Romorantin]
-
A.
Romorantin-Lanthenay
chosen
Romorantin-Lanthenay is a commune in central France known as a historic town in the Loir-et-Cher department and a gateway to the Sologne region.
-
B.
Taradeau
Taradeau is a small commune in the Var department of southeastern France, known for its Provençal countryside, vineyards, and proximity to the Massif des Maures.
-
C.
Miromesnil
Miromesnil is a Paris Métro station in the 8th arrondissement, serving as an interchange between lines 9 and 13 near the Élysée Palace.
-
D.
Bertrée
Bertrée is a village in the municipality of Hannut in the province of Liège, Belgium.
-
E.
Roannais
Roannais is a natural region in central France known for its rolling countryside, agricultural landscapes, and proximity to the upper Loire River.
- 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733edab248190b2cf7f7bc2684468 |
completed | April 9, 2026, 5:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de8546b41081909e13152c4df2eb1c |
completed | April 14, 2026, 6:19 p.m. |
Created at: April 8, 2026, 9:18 p.m.