Triple
T3931110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castelsarrasin |
E90795
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object | Moissac |
E164949
|
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: Moissac | Statement: [Castelsarrasin, sharesBorderWith, Moissac]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Moissac Context triple: [Castelsarrasin, sharesBorderWith, Moissac]
-
A.
Moissac
chosen
Moissac is a historic town in southern France renowned for its Romanesque abbey and cloister, which are listed as a UNESCO World Heritage Site.
-
B.
Figeac
Figeac is a historic town in southwestern France known for its medieval architecture and as the birthplace of Jean-François Champollion, who deciphered Egyptian hieroglyphs.
-
C.
Marciac
Marciac is a small town in southwestern France renowned for hosting the annual Jazz in Marciac festival, one of Europe’s major jazz events.
-
D.
Sarlat-la-Canéda
Sarlat-la-Canéda is a well-preserved medieval town in southwestern France, renowned for its historic architecture, cobbled streets, and vibrant markets in the Périgord Noir region.
-
E.
Ribérac
Ribérac is a small historic town in southwestern France’s Dordogne department, known for its traditional markets and rural charm.
- 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_69aed95f26e0819094b0e71974543a19 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeda98058819094dd6ab223670860 |
completed | March 9, 2026, 3:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b576852d0c819083d377bab6799ec7 |
completed | March 14, 2026, 2:53 p.m. |
Created at: March 9, 2026, 3:23 p.m.