Triple
T22533054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bourse de Commerce |
E557091
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Les Halles |
—
|
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: Les Halles | Statement: [Bourse de Commerce, locatedNear, Les Halles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Les Halles Context triple: [Bourse de Commerce, locatedNear, Les Halles]
-
A.
Les Halles
chosen
Les Halles is a major underground transport hub and commercial area in central Paris, historically known as the city’s main market district.
-
B.
Halle aux Grains
Halle aux Grains is a former grain market in Toulouse, France, now renowned as a major concert hall and cultural venue.
-
C.
The Galeries
The Galeries is a contemporary shopping and dining complex in Sydney’s central business district, known for its mix of fashion, lifestyle stores, eateries, and art-focused spaces.
-
D.
Marché Poncelet
Marché Poncelet is a traditional open-air food market in Paris known for its high-quality produce, specialty shops, and lively neighborhood atmosphere.
-
E.
Marché Paul Bert
Marché Paul Bert is a renowned section of the Saint-Ouen flea market in Paris, known for its high-quality antiques, vintage furniture, and decorative arts.
- 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed88cf08190ae7e5b6bf9a80372 |
completed | April 29, 2026, 1:28 a.m. |
Created at: April 16, 2026, 8:51 p.m.