Triple

T18424991
Position Surface form Disambiguated ID Type / Status
Subject Martin Behaim E442114 entity
Predicate familyName P18 FINISHED
Object Behaim 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: Behaim | Statement: [Martin Behaim, familyName, Behaim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Behaim
Context triple: [Martin Behaim, familyName, Behaim]
  • A. Behaim chosen
    Behaim is a German surname most notably associated with Martin Behaim, a 15th-century cartographer credited with creating one of the earliest surviving terrestrial globes.
  • B. Dasman
    Dasman is a coastal district in Kuwait City known for its historic palace and strategic location along the Persian Gulf.
  • C. El Hajeb
    El Hajeb is a town and provincial capital in northern Morocco, situated in the Fès-Meknès region.
  • D. Behmenburg
    Behmenburg is the birth surname of Dutch-born American supermodel and influential 1960s–70s modeling agency founder Wilhelmina Cooper.
  • E. Bahen
    Bahen is an honorific title used in parts of South Asia to respectfully address a woman, roughly equivalent to “sister.”
  • 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_69d8b9eb8a508190a942fd75ebd8b1dc completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e51b1149788190ad7c453547a6e07c completed April 19, 2026, 6:12 p.m.
Created at: April 10, 2026, 10:47 a.m.