Triple

T6932858
Position Surface form Disambiguated ID Type / Status
Subject Bostan E160478 entity
Predicate connectsBetween P72432 FINISHED
Object Quetta E31430 NE FINISHED

How this triple was built (3 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: Quetta | Statement: [Bostan, connectsBetween, Quetta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Quetta
Context triple: [Bostan, connectsBetween, Quetta]
  • A. Quetta chosen
    Quetta is a major city in western Pakistan known as the provincial capital of Balochistan and a key commercial and military center near the Afghan border.
  • B. Peshawar
    Peshawar is one of Pakistan’s oldest and largest cities, a historic cultural and economic hub located near the Khyber Pass in the country’s northwest.
  • C. Shujabad
    Shujabad is a city in southern Punjab, Pakistan, known for its agricultural economy and proximity to the regional center of Multan.
  • D. Turbat
    Turbat is a major city in southern Balochistan, Pakistan, known as a commercial and cultural center of the Makran region.
  • E. Multan
    Multan is a historic city in southern Punjab, Pakistan, renowned as a major cultural, commercial, and Sufi spiritual center with a legacy spanning over two millennia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: connectsBetween
Context triple: [Bostan, connectsBetween, Quetta]
  • A. connectsTo
    Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
  • B. bridgesBetween chosen
    Indicates a relationship where something connects or links two otherwise separate entities, contexts, or states, enabling interaction or transition between them.
  • C. connectsUnder
    Indicates that one entity forms a connection to another entity by passing beneath or under it.
  • D. connectedByStraitTo
    Indicates that one entity is geographically linked to another by a narrow body of water known as a strait.
  • E. connectsViaCanal
    Indicates that one entity is linked or joined to another by means of a canal.
  • F. None of above.

Provenance (4 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_69c6884e15208190b9e91487eaafcf85 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e0c74fe48190aeaa018631e52ef6 completed March 27, 2026, 7:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7d36fd638819095d7a431026905f7 completed March 28, 2026, 1:11 p.m.
PD Predicate disambiguation batch_69c6d7bd5a388190a57a96d925696ff6 completed March 27, 2026, 7:17 p.m.
Created at: March 27, 2026, 2:27 p.m.