Triple

T393679
Position Surface form Disambiguated ID Type / Status
Subject Johan de Witt E8933 entity
Predicate residence P75 FINISHED
Object Dordrecht E40368 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: Dordrecht | Statement: [Johan de Witt, residence, Dordrecht]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dordrecht
Context triple: [Johan de Witt, residence, Dordrecht]
  • A. Dordrecht chosen
    Dordrecht is a historic Dutch city in South Holland known as one of the oldest trading centers in the Netherlands, situated strategically within the Rhine–Meuse–Scheldt river delta.
  • B. Middelburg
    Middelburg is a historic Dutch city in the province of Zeeland that served as an important maritime and trading center during the era of the Dutch East India Company.
  • C. Delfzijl
    Delfzijl is a port town in the northeast of the Netherlands, known for its maritime industry and location on the Ems estuary near the German border.
  • D. Groningen
    Groningen is a historic province in the northern Netherlands, known for its university city of the same name, flat landscapes, and rich maritime and agricultural heritage.
  • E. Rotterdam
    Rotterdam is a major Dutch port city known for having one of the world’s largest harbors and striking modern architecture.
  • 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_69a2e7f55c60819097aff65ea2ca2832 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec7637c08190b695ec640edbf6c2 completed Feb. 28, 2026, 1:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7cf473e48819095390a5904429a9c completed March 4, 2026, 6:20 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.