Triple

T10556545
Position Surface form Disambiguated ID Type / Status
Subject Ndjolé E249100 entity
Predicate connectsToCityByRail P71547 FINISHED
Object Franceville E871350 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: Franceville | Statement: [Ndjolé, connectsToCityByRail, Franceville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franceville
Context triple: [Ndjolé, connectsToCityByRail, Franceville]
  • A. Franceville chosen
    Franceville is one of the largest cities in Gabon, serving as a major economic and administrative center in the country’s southeastern region.
  • B. Ribeauville
    Ribeauville is a small French commune located in northern France within the administrative area of the Nord department.
  • C. Philippeville
    Philippeville is a coastal city in northeastern Algeria, historically known for its role in the Algerian War of Independence and now officially called Skikda.
  • D. Philippeville
    Philippeville is a historic town in southern Belgium known for its former fortress and location in the Walloon region.
  • E. Franconville
    Franconville is a suburban commune in the northwestern outskirts of Paris, France, known for its residential character and location within the Val-d'Oise department.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d52713eaa48190936b4b15e2c7e827 completed April 7, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69d96b474a248190b46c31e8e0008f9f completed April 10, 2026, 9:27 p.m.
Created at: April 6, 2026, 12:35 p.m.