Triple
T27261598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dreux |
E687778
|
entity |
| Predicate | hasRoyalChapel |
P175973
|
FINISHED |
| Object | Chapelle Royale de Dreux |
—
|
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: Chapelle Royale de Dreux | Statement: [Dreux, hasRoyalChapel, Chapelle Royale de Dreux]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoyalChapel Context triple: [Dreux, hasRoyalChapel, Chapelle Royale de Dreux]
-
A.
hasRoyalHouse
Indicates that an entity is associated with or belongs to a particular royal house or dynasty.
-
B.
hasRoyalMuseum
Indicates that an entity possesses or is associated with a royal museum, typically as its location, owner, or host.
-
C.
hasRoyalArchive
Indicates that an entity maintains or possesses an official royal archive or collection of records associated with royalty.
-
D.
containsRoyalResidence
Indicates that a location includes or encompasses a residence used by royalty.
-
E.
hasRoyalPews
Indicates that a place, typically a religious or ceremonial venue, contains special seating areas reserved for royalty.
- F. None of above. chosen
Provenance (4 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_69ef3557abc481908bf3c146f0f3356a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f6db3606808190a80c6e9f5da5b33e |
completed | May 3, 2026, 5:20 a.m. |
| PD | Predicate disambiguation | batch_69f6d82adfa481908a5e196d2e18c73f |
completed | May 3, 2026, 5:07 a.m. |
| PDg | Predicate description generation | batch_69f6db1bc348819097c844f76e2fa4fe |
completed | May 3, 2026, 5:20 a.m. |
Created at: April 27, 2026, 10:53 a.m.