Triple
T11134989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Friedrichsdorf |
E263386
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Houilles |
E227648
|
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: Houilles | Statement: [Friedrichsdorf, hasTwinTown, Houilles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Houilles Context triple: [Friedrichsdorf, hasTwinTown, Houilles]
-
A.
Houilles
chosen
Houilles is a suburban commune in north-central France, located in the western outskirts of Paris within the Yvelines department.
-
B.
Valenciennes
Valenciennes is a historic industrial city in northern France near the Belgian border, known for its former coal and steel industries and its rich artistic and architectural heritage.
-
C.
Beauvais
Beauvais is a historic city in northern France known for its impressive Gothic cathedral and role as the capital of the Oise department.
-
D.
Bressuire
Bressuire is a historic town in western France known for its medieval castle and role as an administrative center in the Deux-Sèvres department.
-
E.
Leulinghem
Leulinghem is a village in northern France historically notable as the site where a major truce was concluded during the Hundred Years' War.
- 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_69d6aa9c0ba08190bbd19c217489b755 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e85daddc8190a1ae2a4a75cc8d50 |
completed | April 9, 2026, 5:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e46308d2f481908827d0d569802f89 |
completed | April 19, 2026, 5:07 a.m. |
Created at: April 8, 2026, 9:28 p.m.