Triple

T7671856
Position Surface form Disambiguated ID Type / Status
Subject Tomb of Sultan Ibrahim E173766 entity
Predicate locatedNear P294 FINISHED
Object Thatta city E32159 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: Thatta city | Statement: [Tomb of Sultan Ibrahim, locatedNear, Thatta city]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thatta city
Context triple: [Tomb of Sultan Ibrahim, locatedNear, Thatta city]
  • A. Amarkot
    Amarkot is an alternative name for Umarkot, a historic town and district in the Sindh province of Pakistan known for its cultural and Mughal-era significance.
  • B. Bannu
    Bannu is a historic city in northwestern Pakistan known as a regional commercial and cultural center in the Khyber Pakhtunkhwa province.
  • C. Thatta chosen
    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.
  • D. Turbat
    Turbat is a major city in southern Balochistan, Pakistan, known as a commercial and cultural center of the Makran region.
  • E. Bin Qasim Town
    Bin Qasim Town is a residential and industrial locality in the eastern part of Karachi, Pakistan, known for its proximity to the Port Qasim industrial area.
  • 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_69c699562484819086752091e3164a27 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c701de94208190a7627521211452dc completed March 27, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c9162ec9ec8190bd48b23b2877ff34 completed March 29, 2026, 12:08 p.m.
Created at: March 27, 2026, 4 p.m.