Triple

T14715195
Position Surface form Disambiguated ID Type / Status
Subject Ilkhan E345658 entity
Predicate hasLastHolder P3710 FINISHED
Object Anushirwan E559556 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: Anushirwan | Statement: [Ilkhan, hasLastHolder, Anushirwan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anushirwan
Context triple: [Ilkhan, hasLastHolder, Anushirwan]
  • A. Anushirvan chosen
    Anushirvan is the honorific title of Khosrow I, the renowned Sasanian king celebrated for his just rule and major administrative and cultural reforms in the Persian Empire.
  • B. Goshtasp
    Goshtasp is a legendary Kayanian king in Persian mythology, best known as the father of the hero Esfandiyar and a patron of Zoroaster.
  • C. Behram
    Behram is an alternative name for the ancient Greek city of Assos, a historic coastal settlement in present-day Turkey known for its classical ruins and scenic Aegean setting.
  • D. Narseh
    Narseh was a Sasanian king of Persia in the early 4th century, known for his inscriptions and rock reliefs and for briefly restoring imperial strength before being defeated by the Romans.
  • E. Shahpur
    Shahpur is a notable town in Bihar, India, recognized as one of the main urban centers of Bhojpur district.
  • 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_69d822e5911c8190ba589f957dbd9ba7 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb98513b081908b230f6ac79c72ad completed April 14, 2026, 10:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe388792688190b1b6eaa8091733fb completed May 8, 2026, 7:24 p.m.
Created at: April 10, 2026, 1:29 a.m.