Triple

T18960770
Position Surface form Disambiguated ID Type / Status
Subject Dani Jackson E463905 entity
Predicate givenName P17 FINISHED
Object Dani 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: Dani | Statement: [Dani Jackson, givenName, Dani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dani
Context triple: [Dani Jackson, givenName, Dani]
  • A. Dani
    Dani is a fictional character played by actress Adria Arjona, known from her role in the fantasy-romance film "Emerald City" and other screen appearances.
  • B. Dani
    The Dani are an indigenous ethnic group of the central highlands of Papua, Indonesia, known for their distinctive traditional dress, terraced agriculture, and complex ritual practices.
  • C. Dani
    Dani is an actor who appears in the film "Day for Night," a classic French movie directed by François Truffaut.
  • D. Dani chosen
    Dani is the given name of Dani Rodrik, a prominent Turkish economist known for his work on globalization and economic development.
  • E. Dani
    Dani is an actor known for playing a leading role in the film "Love on the Run."
  • 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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d5d2b1c08190a4a32036c70c7746 completed April 20, 2026, 7:29 a.m.
Created at: April 10, 2026, noon