Triple

T5385595
Position Surface form Disambiguated ID Type / Status
Subject Makatib E120193 entity
Predicate relatedWork P37 FINISHED
Object Fihi ma fihi E120192 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: Fihi ma fihi | Statement: [Makatib, relatedWork, Fihi ma fihi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fihi ma fihi
Context triple: [Makatib, relatedWork, Fihi ma fihi]
  • A. Fihi Ma Fihi chosen
    Fihi Ma Fihi is a collection of prose discourses by the Persian Sufi mystic Rumi, presenting his spiritual teachings and interpretations of Islamic mysticism.
  • B. Filerimos
    Filerimos is a historic hill on the island of Rhodes in Greece, known for its medieval monastery, ancient acropolis ruins, and panoramic views over the surrounding area.
  • C. First of the First
    First of the First is the nickname of the 1st Battalion, 1st Marines, a storied infantry battalion of the United States Marine Corps known for its long combat history.
  • D. De fide
    De fide is a theological treatise by Ambrose of Milan that systematically defends and explains the Nicene Christian doctrine of the Trinity.
  • E. Uno dei tanti
    "Uno dei tanti" is an Italian song that gained international recognition after being adapted into English as "I (Who Have Nothing)."
  • 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_69bd46354c648190a38b26f107010a96 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd86f5a7388190aa4ba2052afca74e completed March 20, 2026, 5:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf295352988190a48d3f9db56fcaf8 completed March 21, 2026, 11:27 p.m.
Created at: March 20, 2026, 2:03 p.m.