Triple

T16567424
Position Surface form Disambiguated ID Type / Status
Subject Abe E402498 entity
Predicate familyName P18 FINISHED
Object Abrams E85537 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: Abrams | Statement: [Abe, familyName, Abrams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abrams
Context triple: [Abe, familyName, Abrams]
  • A. Abrams chosen
    Abrams is a common English-language surname borne by various notable individuals across fields such as entertainment, politics, and the military.
  • B. Kraftt
    Kraftt is an alternative or variant form of the name "Kraft," likely referring to the same or a closely related entity, such as the well-known food brand or surname.
  • C. Alion
    Alion is a barangay (village-level administrative division) within the municipality of Mariveles in the province of Bataan, Philippines.
  • D. Nortrup
    Nortrup is a small municipality in Lower Saxony, Germany, situated within the Artland region.
  • E. Abrams Image
    Abrams Image is an imprint of the art and illustrated book publisher Abrams, specializing in visually driven, pop culture–oriented titles.
  • 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_69d8838648088190acf97ef11fc3f61b completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e35772f6608190a125c7d3c199c3e2 completed April 18, 2026, 10:05 a.m.
NED1 Entity disambiguation (via context triple) batch_6a007da4b60c8190a682d20aa881792c completed May 10, 2026, 12:44 p.m.
Created at: April 10, 2026, 5:16 a.m.