Triple

T20565950
Position Surface form Disambiguated ID Type / Status
Subject Tenggelamnya Kapal Van der Wijck E504965 entity
Predicate character P662 FINISHED
Object Hayati 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: Hayati | Statement: [Tenggelamnya Kapal Van der Wijck, character, Hayati]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hayati
Context triple: [Tenggelamnya Kapal Van der Wijck, character, Hayati]
  • A. Hayati chosen
    Hayati is the central female character in Hamka’s classic Indonesian novel "Tenggelamnya Kapal Van der Wijck," whose tragic love story with Zainuddin highlights themes of social class, tradition, and heartbreak.
  • B. Hayat
    Hayat is a novel by Turkish author Ayşe Kulin, known for its emotionally rich storytelling and exploration of personal and social themes.
  • C. Kazi Hayat
    Kazi Hayat is a prominent Bangladeshi film director, screenwriter, and actor known for his influential contributions to commercial Bengali cinema.
  • D. Hayatilae
    Hayatilae is another name for the Hephthalite Empire, a powerful nomadic confederation that dominated parts of Central Asia, Afghanistan, and northern India in the 5th–6th centuries CE.
  • E. חיים
    חיים is a common Hebrew given name meaning "life," frequently used in Jewish communities worldwide.
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a228948190b47a3a61f239e00d completed April 20, 2026, 10:24 p.m.
Created at: April 16, 2026, 11:39 a.m.