Triple
T16214329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-Mihiel |
E393545
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Commercy |
E393544
|
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: Commercy | Statement: [Saint-Mihiel, near, Commercy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Commercy Context triple: [Saint-Mihiel, near, Commercy]
-
A.
Commercy
chosen
Commercy is a small town in northeastern France best known for its madeleine pastries and its role as an administrative center in the Meuse department.
-
B.
Commerce
Commerce is a small city in northeast Texas known for hosting Texas A&M University–Commerce and functioning as part of the greater Dallas–Fort Worth region.
-
C.
Commerce
Commerce is a city in Los Angeles County, California, known for its industrial base, rail yards, and large outlet shopping center.
-
D.
Commerce
Commerce is a Paris Métro station located in the 15th arrondissement, serving the surrounding residential and commercial neighborhood.
-
E.
The Business
The Business is a British television series featuring actress Caroline Harker in a prominent role.
- 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_69d87f1f5bd08190bd01cac0d5b9d2ef |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e227f393e08190be93400d754f0a2d |
completed | April 17, 2026, 12:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000794e6c881909c4521e4dd031971 |
completed | May 10, 2026, 4:20 a.m. |
Created at: April 10, 2026, 5:03 a.m.