Triple
T15722146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue Monge |
E381122
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Place Monge |
E254186
|
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: Place Monge | Statement: [Rue Monge, hasPart, Place Monge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Place Monge Context triple: [Rue Monge, hasPart, Place Monge]
-
A.
Place Monge
chosen
Place Monge is a small Parisian square in the Latin Quarter known for its local market and proximity to historic and academic landmarks.
-
B.
La Mongie
La Mongie is a French Pyrenean ski resort village known as a gateway to the Pic du Midi de Bigorre and its observatory.
-
C.
Montélier
Montélier is a commune in southeastern France’s Drôme department, situated near the town of Romans-sur-Isère.
-
D.
Place Maubert
Place Maubert is a historic public square in Paris’s 5th arrondissement, known for its traditional market and proximity to the Latin Quarter and the Maubert–Mutualité metro station.
-
E.
Marcelin
Marcelin is a French diminutive form of the given name Marcel, often used as an affectionate or familiar variant.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fb0b51081908e652ec4992296fa |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82f464008190ae0e79f50b9b3eb3 |
completed | May 9, 2026, 6:54 p.m. |
Created at: April 10, 2026, 4:45 a.m.