Triple

T21049739
Position Surface form Disambiguated ID Type / Status
Subject Orlando (Italian) E518543 entity
Predicate associatedWith P37 FINISHED
Object Roncesvalles 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: Roncesvalles | Statement: [Orlando (Italian), associatedWith, Roncesvalles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roncesvalles
Context triple: [Orlando (Italian), associatedWith, Roncesvalles]
  • A. Roncesvalles chosen
    Roncesvalles is a small historic village and pilgrimage stop in the Pyrenees of northern Spain, famed as a key waypoint on the Camino de Santiago and the legendary site of Charlemagne’s rear-guard battle.
  • B. Lavezares
    Lavezares is a coastal municipality in the province of Northern Samar in the Philippines, known for its fishing communities and island landscapes.
  • C. Escaudain
    Escaudain is a commune in northern France’s Nord department, historically shaped by coal mining and situated within the industrial Valenciennes area.
  • D. Navarcles
    Navarcles is a municipality in the comarca of Bages in Catalonia, Spain, known for its location near the Llobregat and Calders rivers.
  • E. Monsaraz
    Monsaraz is a historic hilltop village in Portugal’s Alentejo region, renowned for its medieval walls, whitewashed houses, and panoramic views over the Alqueva reservoir.
  • 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_69e0b5053ac48190921529544959e906 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fd79830881909fdac2f0ea48d28c completed April 21, 2026, 4:30 a.m.
Created at: April 16, 2026, 2:34 p.m.