Triple

T12749974
Position Surface form Disambiguated ID Type / Status
Subject Hermann Kosterlitz E304704 entity
Predicate alsoKnownAs P39 FINISHED
Object H. Koster
H. Koster is an alternative name for Hermann Kosterlitz, the German-born British neuroscientist renowned for his pioneering work on endorphins and pain regulation.
 E1001291 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: H. Koster | Statement: [Hermann Kosterlitz, alsoKnownAs, H. Koster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: H. Koster
Context triple: [Hermann Kosterlitz, alsoKnownAs, H. Koster]
  • A. T. H. Korf
    T. H. Korf is a mycologist recognized for his taxonomic work in fungal classification, including the naming of the family Ophiostomataceae.
  • B. Cornelis H. A. Koster
    Cornelis H. A. Koster was a Dutch computer scientist known for his contributions to programming language design and formal language theory.
  • C. C. van der Leeuw
    C. van der Leeuw was a Dutch engineer and architect known for designing the Willemsbrug in Rotterdam.
  • D. J.M.A. Biesheuvel
    J.M.A. Biesheuvel was a Dutch writer renowned for his distinctive, often autobiographical short stories that blend humor with existential and psychological themes.
  • E. Peter Oskam
    Peter Oskam is a Dutch politician and former judge who has served as mayor of Capelle aan den IJssel.
  • 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: H. Koster
Triple: [Hermann Kosterlitz, alsoKnownAs, H. Koster]
Generated description
H. Koster is an alternative name for Hermann Kosterlitz, the German-born British neuroscientist renowned for his pioneering work on endorphins and pain regulation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: H. Koster
Target entity description: H. Koster is an alternative name for Hermann Kosterlitz, the German-born British neuroscientist renowned for his pioneering work on endorphins and pain regulation.
  • A. T. H. Korf
    T. H. Korf is a mycologist recognized for his taxonomic work in fungal classification, including the naming of the family Ophiostomataceae.
  • B. Cornelis H. A. Koster
    Cornelis H. A. Koster was a Dutch computer scientist known for his contributions to programming language design and formal language theory.
  • C. C. van der Leeuw
    C. van der Leeuw was a Dutch engineer and architect known for designing the Willemsbrug in Rotterdam.
  • D. J.M.A. Biesheuvel
    J.M.A. Biesheuvel was a Dutch writer renowned for his distinctive, often autobiographical short stories that blend humor with existential and psychological themes.
  • E. Peter Oskam
    Peter Oskam is a Dutch politician and former judge who has served as mayor of Capelle aan den IJssel.
  • 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_69d7bdf1fcd081909ffb0e0d6fa3a07d completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96bd75f508190aaae0969f33d1523 completed April 10, 2026, 9:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69f67c964c508190b4d6a094b388280b completed May 2, 2026, 10:37 p.m.
NEDg Description generation batch_69f67d663fd08190a00b30a7ff260c70 completed May 2, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69f67e0f48e4819085905564f5540f37 completed May 2, 2026, 10:43 p.m.
Created at: April 9, 2026, 5:27 p.m.