Triple

T17641573
Position Surface form Disambiguated ID Type / Status
Subject William Saroyan E429241 entity
Predicate hasPseudonym P3799 FINISHED
Object Sirak Goryan 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: Sirak Goryan | Statement: [William Saroyan, hasPseudonym, Sirak Goryan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sirak Goryan
Context triple: [William Saroyan, hasPseudonym, Sirak Goryan]
  • A. Sirak Goryan chosen
    Sirak Goryan is a lesser-known pseudonym used by Armenian-American writer and playwright William Saroyan.
  • B. Sahak
    Sahak is an Armenian given name most famously borne by Sahak Partev, a prominent 5th-century Catholicos of the Armenian Apostolic Church and key figure in early Armenian Christianity.
  • C. Shabuhragan
    Shabuhragan is a foundational Manichaean scripture, traditionally attributed to the prophet Mani, that outlines the religion’s dualistic cosmology and teachings.
  • D. Byureghavan
    Byureghavan is a small town in Armenia known for its industrial activity and proximity to the capital, Yerevan.
  • E. Mardik
    Mardik is the given name of Mardik Martin, an American screenwriter known for his collaborations with director Martin Scorsese.
  • 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_69d889e2c2608190b762e76d9b2262f1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46de645208190a40dcf443f8afd82 completed April 19, 2026, 5:53 a.m.
Created at: April 10, 2026, 6:03 a.m.