Triple

T20650181
Position Surface form Disambiguated ID Type / Status
Subject Guise E507468 entity
Predicate nearbyCity P350 FINISHED
Object Laon 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: Laon | Statement: [Guise, nearbyCity, Laon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laon
Context triple: [Guise, nearbyCity, Laon]
  • A. Laon chosen
    Laon is a historic hilltop city in northern France known for its well-preserved medieval architecture and impressive Gothic cathedral.
  • B. Troyes
    Troyes is a historic city in northeastern France, known for its well-preserved medieval old town, half-timbered houses, and Gothic churches.
  • C. Reims
    Reims is a historic city in northeastern France known for its Gothic cathedral, role in French coronations, and significance during both World Wars.
  • D. Draveil
    Draveil is a suburban commune in the southern Île-de-France region of France, located near Paris along the Seine River.
  • E. Creil
    Creil is a village in the Dutch province of Flevoland, located in the reclaimed polder landscape of the Noordoostpolder.
  • 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_69e0b4bf58c081908e52a4500e03ff83 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af2133048190a6308074a3b3347e completed April 20, 2026, 10:56 p.m.
Created at: April 16, 2026, 11:43 a.m.