Triple
T6146744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lutetia |
E137096
|
entity |
| Predicate | hasRemainsAt |
P16216
|
FINISHED |
| Object | Arènes de Lutèce |
E254182
|
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: Arènes de Lutèce | Statement: [Lutetia, hasRemainsAt, Arènes de Lutèce]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arènes de Lutèce Context triple: [Lutetia, hasRemainsAt, Arènes de Lutèce]
-
A.
Arènes de Lutèce
chosen
Arènes de Lutèce is an ancient Roman amphitheater in Paris, one of the city's oldest monuments and a rare remnant of the Gallo-Roman era.
-
B.
Arènes de Nîmes
Arènes de Nîmes is a well-preserved Roman amphitheatre in the French city of Nîmes, renowned for its ancient architecture and continued use for cultural events.
-
C.
Hippodrome de Vincennes
Hippodrome de Vincennes is a major Parisian horse racing track renowned as the home of French trotting races.
-
D.
Stade Auguste-Bonal
Stade Auguste-Bonal is a football stadium in Montbéliard, France, best known as the long-time home ground of FC Sochaux-Montbéliard.
-
E.
Hippodrome d’Auteuil
Hippodrome d’Auteuil is a renowned Parisian racecourse specializing in steeplechase and jump racing, located on the western edge of the city.
- 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_69c008a2c6308190a56519b22d55d083 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05cdeeaa88190948d9db6eb2dbf46 |
completed | March 22, 2026, 9:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c135fe8ae48190bfb20c335c7d32be |
completed | March 23, 2026, 12:45 p.m. |
Created at: March 22, 2026, 4:16 p.m.