Triple

T13770615
Position Surface form Disambiguated ID Type / Status
Subject Zebulon E330869 entity
Predicate hasShortForm P43 FINISHED
Object Zeb E114761 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: Zeb | Statement: [Zebulon, hasShortForm, Zeb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zeb
Context triple: [Zebulon, hasShortForm, Zeb]
  • A. Zeb chosen
    Zeb is a central character in Margaret Atwood's dystopian novel "MaddAddam," known for his complex past and role in the post-apocalyptic narrative.
  • B. Zebo
    Zebo is the surname of Irish rugby union player Simon Zebo, known for his try-scoring prowess with Munster and Ireland.
  • C. Zebilla
    Zebilla is a town in Ghana’s Upper East Region that serves as a local commercial and administrative center.
  • D. Zeeb
    Zeeb is a variant transliteration of the Hebrew name Ze'ev, which means "wolf" and is known from its appearance in the Hebrew Bible.
  • E. Zeke
    Zeke is a central male character in the romantic comedy film "Think Like a Man," known for navigating modern dating dynamics alongside a group of friends influenced by a relationship advice book.
  • 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_69d81c583b0081909e408a17db517a21 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0235aea881909ab4c721db081b00 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a86907cc8190a6a6b475d08f0dc7 completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:10 p.m.