Triple

T16768482
Position Surface form Disambiguated ID Type / Status
Subject Johan Harmen Rudolf Köhler E407529 entity
Predicate givenName P17 FINISHED
Object Harmen
Harmen is the given name of Johan Harmen Rudolf Köhler, a Dutch-born military officer who became a general in the Royal Netherlands East Indies Army in the 19th century.
E1232204 NE FINISHED

How this triple was built (4 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: Harmen | Statement: [Johan Harmen Rudolf Köhler, givenName, Harmen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harmen
Context triple: [Johan Harmen Rudolf Köhler, givenName, Harmen]
  • A. Hendrik
    Hendrik is a masculine given name of Germanic origin, commonly used in Dutch- and German-speaking countries and related to the name Henry.
  • B. Leendert
    Leendert is a Dutch masculine given name, notably borne by mathematician Bartel Leendert van der Waerden.
  • C. Dirck
    Dirck is a Dutch masculine given name historically borne by several notable figures, including artists of the Dutch Golden Age.
  • D. Joris
    Joris is a Dutch designer best known for his innovative, technology-driven furniture and experimental design projects.
  • E. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Harmen
Triple: [Johan Harmen Rudolf Köhler, givenName, Harmen]
Generated description
Harmen is the given name of Johan Harmen Rudolf Köhler, a Dutch-born military officer who became a general in the Royal Netherlands East Indies Army in the 19th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harmen
Target entity description: Harmen is the given name of Johan Harmen Rudolf Köhler, a Dutch-born military officer who became a general in the Royal Netherlands East Indies Army in the 19th century.
  • A. Hendrik
    Hendrik is a masculine given name of Germanic origin, commonly used in Dutch- and German-speaking countries and related to the name Henry.
  • B. Leendert
    Leendert is a Dutch masculine given name, notably borne by mathematician Bartel Leendert van der Waerden.
  • C. Dirck
    Dirck is a Dutch masculine given name historically borne by several notable figures, including artists of the Dutch Golden Age.
  • D. Joris
    Joris is a Dutch designer best known for his innovative, technology-driven furniture and experimental design projects.
  • E. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • F. None of above. chosen

Provenance (5 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b0349bc88190938750f1e5af192a completed April 18, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a533e83481909966a7b86c8c8e64 completed May 10, 2026, 3:33 p.m.
NEDg Description generation batch_6a00a6d6a6d08190b103c2dfd30f0e28 completed May 10, 2026, 3:40 p.m.
NED2 Entity disambiguation (via description) batch_6a00a749f2688190af57bd13b9dedeb1 completed May 10, 2026, 3:42 p.m.
Created at: April 10, 2026, 5:21 a.m.