Triple

T23232643
Position Surface form Disambiguated ID Type / Status
Subject Joan Blackman E581201 entity
Predicate coStarredWith P14987 FINISHED
Object Marta Kristen 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: Marta Kristen | Statement: [Joan Blackman, coStarredWith, Marta Kristen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marta Kristen
Context triple: [Joan Blackman, coStarredWith, Marta Kristen]
  • A. Marta Kristen chosen
    Marta Kristen is an American actress best known for playing Judy Robinson on the 1960s science fiction television series "Lost in Space."
  • B. Magdalena Luther
    Magdalena Luther was the beloved daughter of Protestant Reformer Martin Luther, remembered particularly for her early death and its profound impact on him.
  • C. Maria Marc
    Maria Marc was a German painter and the second wife of Expressionist artist Franz Marc, known for her own artistic work and for preserving and promoting her husband's legacy.
  • D. Eleona Church
    Eleona Church is a Christian church on Jerusalem’s Mount of Olives traditionally associated with Jesus’ teaching of the Lord’s Prayer.
  • E. Marta
    Marta is a feminine given name commonly used in many European and Latin American countries, often considered a variant of the name Martha.
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192e70b2c8190abede6e3cd9344f7 completed April 29, 2026, 5:11 a.m.
Created at: April 17, 2026, 4:09 p.m.