Triple

T20931684
Position Surface form Disambiguated ID Type / Status
Subject Hushang E515485 entity
Predicate successor P78 FINISHED
Object Tahmuras 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: Tahmuras | Statement: [Hushang, successor, Tahmuras]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tahmuras
Context triple: [Hushang, successor, Tahmuras]
  • A. Tahmuras chosen
    Tahmuras is a legendary king in Iranian mythology, famed in the Shahnameh for subduing demons and advancing civilization during the early mythical dynasties.
  • B. Khirsu
    Khirsu is a small scenic hill town in Uttarakhand, India, known for its tranquil environment and panoramic views of the Himalayan peaks.
  • C. Ziusuddu
    Ziusuddu is a legendary Sumerian figure known as the hero of an ancient Mesopotamian flood myth, often compared to the biblical Noah.
  • D. Ur-Baba
    Ur-Baba was a ruler (ensi) of the Sumerian city-state of Lagash in the late 3rd millennium BCE, known as the predecessor of the famous governor Gudea.
  • E. Siamun
    Siamun was a pharaoh of Egypt’s 21st Dynasty who ruled from Tanis and is known for consolidating power in the Nile Delta during a period of political fragmentation.
  • 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_69e0b4fb431c8190b9d40e6a72f0cc87 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6f65681b4819083c7ef6b44ba4bdb completed April 21, 2026, 4 a.m.
Created at: April 16, 2026, 12:49 p.m.