Triple

T2466132
Position Surface form Disambiguated ID Type / Status
Subject Andi E55251 entity
Predicate relatedName P3889 FINISHED
Object Andreas E8082 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: Andreas | Statement: [Andi, relatedName, Andreas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andreas
Context triple: [Andi, relatedName, Andreas]
  • A. Andreas chosen
    Andreas is a masculine given name of Greek origin, commonly used in various European and international cultures.
  • B. Johan
    Johan is the given first name of J. Erik Jonsson, an American businessman and philanthropist who co-founded Texas Instruments and served as mayor of Dallas.
  • C. Andreas Hermes
    Andreas Hermes was a German politician and agricultural expert who served in high-level government roles during the Weimar Republic and later became a prominent figure in postwar Christian democratic politics.
  • D. Anders
    Anders is a Scandinavian given name, commonly used in countries like Sweden, Norway, and Denmark, and is a variant of the name Andrew.
  • E. Johanus
    Johanus is a given name, likely a variant or diminutive of Johan, used as a personal first name in some cultures.
  • 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_69ab49e3622c8190ad22afa2c4fbb807 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd122db8881909ef3c0a1df7ff7a5 completed March 7, 2026, 7:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69af2b7af0d4819080fda496670bc5d7 completed March 9, 2026, 8:20 p.m.
Created at: March 6, 2026, 9:44 p.m.