Triple

T21682088
Position Surface form Disambiguated ID Type / Status
Subject Tus, Iran E535132 entity
Predicate hasNotablePerson P304 FINISHED
Object Ferdowsi 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: Ferdowsi | Statement: [Tus, Iran, hasNotablePerson, Ferdowsi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ferdowsi
Context triple: [Tus, Iran, hasNotablePerson, Ferdowsi]
  • A. Ferdowsi chosen
    Ferdowsi was a renowned 10th–11th century Persian poet best known for composing the epic Shahnameh, a cornerstone of Persian literature and cultural identity.
  • B. Rudaki
    Rudaki was a pioneering 10th-century Persian poet often regarded as the father of New Persian literature.
  • C. Nizami Ganjavi
    Nizami Ganjavi was a 12th-century Persian poet renowned for his romantic epic masterpieces, especially the Khamsa (Quintet), which profoundly influenced Persian and wider Islamic literature.
  • D. Hafez
    Hafez was a 14th-century Persian lyric poet renowned for his ghazals, which explore themes of love, mysticism, and the divine, and remain central to Persian literature and culture.
  • E. Ahmad Yasawi
    Ahmad Yasawi was a 12th-century Turkic Sufi mystic and poet whose teachings deeply influenced the spread and development of Islam and Sufism in Central Asia and the Turkic world.
  • 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_69e0c469b6ec8190aee4cadd1527db91 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef96c69990819088a1134ecea09099 completed April 27, 2026, 5:03 p.m.
Created at: April 16, 2026, 6:43 p.m.