Triple

T20365586
Position Surface form Disambiguated ID Type / Status
Subject Sultan Ahmad Sanjar E496898 entity
Predicate regnalName P744 FINISHED
Object Sanjar 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: Sanjar | Statement: [Sultan Ahmad Sanjar, regnalName, Sanjar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanjar
Context triple: [Sultan Ahmad Sanjar, regnalName, Sanjar]
  • A. Sanjar chosen
    Sanjar was a prominent 12th-century Seljuk ruler who governed the eastern provinces of the empire and is often regarded as its last great sultan.
  • B. Qalat
    Qalat is a key urban center and provincial capital in southern Afghanistan, known for its strategic location and historical fortifications.
  • C. Jahanabad
    Jahanabad is a locality that forms one of the neighborhoods within the town of SITE Town.
  • D. Musa Qala
    Musa Qala is a town and district center in southern Afghanistan that has been a focal point of conflict and military operations, particularly during the Afghan War.
  • E. Mahmudabad
    Mahmudabad is a coastal city in northern Iran, situated along the Caspian Sea in Mazandaran Province and known for its beaches and tourism.
  • 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_69e0b4a4f9b081908a5a021919c21ccb completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67871bfdc8190948c46497cd675c9 completed April 20, 2026, 7:03 p.m.
Created at: April 16, 2026, 11:26 a.m.