Triple

T23251874
Position Surface form Disambiguated ID Type / Status
Subject Used to Love You E581751 entity
Predicate writer P1360 FINISHED
Object Jonathan Rotem 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: Jonathan Rotem | Statement: [Used to Love You, writer, Jonathan Rotem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jonathan Rotem
Context triple: [Used to Love You, writer, Jonathan Rotem]
  • A. Michael Shalev
    Michael Shalev is an Israeli sociologist and academic known for his work on political economy, welfare states, and labor relations.
  • B. Jonathan Reuven Rotem chosen
    Jonathan Reuven Rotem is an Israeli-American record producer and songwriter known for crafting pop and hip-hop hits for artists such as Rihanna, Jason Derulo, and Sean Kingston.
  • C. Yair Tzaban
    Yair Tzaban is an Israeli politician and social activist known for his leadership in the left-wing Mapam party and his advocacy for peace, civil rights, and social justice.
  • D. Giora Rotman
    Giora Rotman is an Israeli architect best known for designing prominent modern high-rise buildings, including some of the country's tallest towers.
  • E. Amiel Ben-Horin
    Amiel Ben-Horin is a central character in the Israeli television drama "Prisoners of War" (Hatufim), which inspired the American series "Homeland."
  • 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f193f7249481909424867e9542d35e completed April 29, 2026, 5:15 a.m.
Created at: April 17, 2026, 4:11 p.m.