Triple

T12058639
Position Surface form Disambiguated ID Type / Status
Subject Indus Highway E287107 entity
Predicate connectsCity P4245 FINISHED
Object Shikarpur E388632 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: Shikarpur | Statement: [Indus Highway, connectsCity, Shikarpur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shikarpur
Context triple: [Indus Highway, connectsCity, Shikarpur]
  • A. Shikarpur chosen
    Shikarpur is a historic city in the Sindh province of Pakistan, known for its old trading heritage and distinctive cultural and architectural traditions.
  • B. Khairpur
    Khairpur is a historic city in Sindh, Pakistan, known for its former princely state status under the Talpur rulers and its rich cultural and architectural heritage.
  • C. Kalhoro
    Kalhoro is a Sindhi tribe historically prominent in the region that provided the ruling family for the Kalhora dynasty in what is now Pakistan.
  • D. Rahim Yar Khan
    Rahim Yar Khan is a major city in southern Punjab, Pakistan, known as an important commercial and agricultural center in the Seraiki-speaking region.
  • E. Vehari
    Vehari is a city in the Punjab province of Pakistan, known as an agricultural and educational hub in the region.
  • 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_69d6ab4780948190bdb9f7620c2ac27e completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9043dbccc8190bf9da181f826f0d8 completed April 10, 2026, 2:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69f62a7a77648190ab2d6bd48821d190 completed May 2, 2026, 4:46 p.m.
Created at: April 8, 2026, 9:47 p.m.