Triple

T19541702
Position Surface form Disambiguated ID Type / Status
Subject Seti II E488920 entity
Predicate spouse P13 FINISHED
Object Takhat 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: Takhat | Statement: [Seti II, spouse, Takhat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Takhat
Context triple: [Seti II, spouse, Takhat]
  • A. Takhat chosen
    Takhat was an ancient Egyptian queen of the 19th Dynasty, known as a royal wife and likely a member of the extended Ramesside royal family.
  • B. Sangi Takht
    Sangi Takht is a town in central Afghanistan that serves as a local administrative and population center within Daykundi Province.
  • C. Takht-e-Nasrati
    Takht-e-Nasrati is a town and administrative tehsil in Pakistan’s Khyber Pakhtunkhwa province, known as one of the key population centers of Karak District.
  • D. Thatta
    Thatta is an ancient city in Pakistan’s Sindh province, renowned for its rich Islamic architectural heritage and role as a major cultural and commercial center in South Asian history.
  • E. Takht-e-Sulaiman
    Takht-e-Sulaiman is a prominent mountain peak in Pakistan revered in local legend and known for its religious and historical significance.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63872fda48190bbb1f465cb7b57fe completed April 20, 2026, 2:30 p.m.
Created at: April 10, 2026, 1:41 p.m.