Triple

T22010784
Position Surface form Disambiguated ID Type / Status
Subject Mol E543566 entity
Predicate hasSubdivision P747 FINISHED
Object Postel NE NERFINISHED

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: Postel | Statement: [Mol, hasSubdivision, Postel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Postel
Context triple: [Mol, hasSubdivision, Postel]
  • A. Postel chosen
    Postel is a surname most prominently associated with Jon Postel, a pioneering computer scientist and key architect of the early Internet.
  • B. Cerf
    Cerf is a surname most prominently associated with Vint Cerf, a pioneering computer scientist often called one of the "fathers of the Internet."
  • C. Selma Hacker
    Selma Hacker is the gruff, deadpan court clerk on the sitcom "Night Court," known for her sardonic wit and no-nonsense demeanor.
  • D. David Finfer
    David Finfer was an American film editor known for his work on a wide range of Hollywood movies across several decades.
  • E. Ray Tomlinson
    Ray Tomlinson was an American computer programmer best known for inventing networked email and introducing the use of the "@" symbol in email addresses.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e2db934819095556760c7d85e4d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127a4338c8190836074d21bfbaf78 completed April 28, 2026, 9:33 p.m.
Created at: April 16, 2026, 8:22 p.m.