Triple

T12528798
Position Surface form Disambiguated ID Type / Status
Subject Unkel E299505 entity
Predicate hasSubdivision P747 FINISHED
Object Heister E799383 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: Heister | Statement: [Unkel, hasSubdivision, Heister]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heister
Context triple: [Unkel, hasSubdivision, Heister]
  • A. de Heister
    De Heister is a German noble family name historically associated with military officers and aristocrats, including the Hessian general Leopold Philip de Heister.
  • B. Heris
    Heris is a city in northwestern Iran known for its traditional handwoven carpets and rugs.
  • C. Haiger chosen
    Haiger is a small town in the German state of Hesse, known for its location in the Lahn-Dill district near the borders with North Rhine-Westphalia and Rhineland-Palatinate.
  • D. Rodemack
    Rodemack is a historic fortified village in northeastern France, renowned for its well-preserved medieval ramparts and picturesque old town.
  • E. Dirck
    Dirck is a Dutch masculine given name historically borne by several notable figures, including artists of the Dutch Golden Age.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9545e90948190980bd4d64964a0f2 completed April 10, 2026, 7:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc674e881908673e1f9103cc8be completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.