Triple

T7737031
Position Surface form Disambiguated ID Type / Status
Subject Esztergom E175407 entity
Predicate hasTwinTown P919 FINISHED
Object Wesel E89464 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: Wesel | Statement: [Esztergom, hasTwinTown, Wesel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wesel
Context triple: [Esztergom, hasTwinTown, Wesel]
  • A. Wesel chosen
    Wesel is a historic city in western Germany, located on the Rhine River in the state of North Rhine-Westphalia.
  • B. Erftstadt
    Erftstadt is a town in the Rhein-Erft district of North Rhine-Westphalia, Germany, located southwest of Cologne and known for its mix of historic villages and suburban residential areas.
  • C. Emmerich am Rhein
    Emmerich am Rhein is a German town on the Rhine River near the Dutch border, known for its historic center and prominent Rhine bridge.
  • D. Bingen am Rhein
    Bingen am Rhein is a historic town in Germany’s Rhineland-Palatinate, known as a gateway to the scenic Upper Middle Rhine Valley with its castles, vineyards, and river landscapes.
  • E. Andernach
    Andernach is a historic German town on the Rhine River in Rhineland-Palatinate, known for its medieval architecture and one of the world’s highest cold-water geysers.
  • 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_69c6995f9c60819092e386192bd63c6f completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7035923108190842025631e2314cc completed March 27, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be3958ac8190a48ba07bd8ea3251 completed March 29, 2026, 5:52 a.m.
Created at: March 27, 2026, 4:07 p.m.