Triple

T1386631
Position Surface form Disambiguated ID Type / Status
Subject Surah Yunus E29860 entity
Predicate name P16 FINISHED
Object Yunus E109128 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: Yunus | Statement: [Surah Yunus, name, Yunus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yunus
Context triple: [Surah Yunus, name, Yunus]
  • A. Yunus chosen
    Yunus is the Arabic form of the name Jonas, commonly associated with the prophet Jonah in Islamic tradition.
  • B. Abdul Latif Jameel
    Abdul Latif Jameel is a Saudi Arabia–based diversified business group and philanthropic organization known for its major investments in automotive, real estate, energy, and its support for global poverty alleviation and development initiatives.
  • C. Jawed Ahmad Karim
    Jawed Ahmad Karim is a German-American computer scientist and internet entrepreneur best known as a co-founder of YouTube and for uploading the platform’s first video, "Me at the zoo."
  • D. Elimah Rabbati
    Elimah Rabbati is a major Kabbalistic work by the 16th-century mystic Moshe Cordovero, offering a systematic and influential exposition of Jewish mystical theology.
  • E. Abdus
    Abdus is a given name most notably borne by Abdus Salam, the Pakistani theoretical physicist and Nobel laureate.
  • 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_69a498dc92f8819094a1108f8ac90f43 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c33b6e108190b6b2bca4ddd97b6c completed March 1, 2026, 10:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69acd48fc7f88190a971e6b6fa01453e completed March 8, 2026, 1:44 a.m.
Created at: March 1, 2026, 7:59 p.m.