Triple

T5409305
Position Surface form Disambiguated ID Type / Status
Subject With Gandhi in Ceylon E120971 entity
Predicate settingLocation P40 FINISHED
Object Colombo E11029 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: Colombo | Statement: [With Gandhi in Ceylon, settingLocation, Colombo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Colombo
Context triple: [With Gandhi in Ceylon, settingLocation, Colombo]
  • A. Colombo chosen
    Colombo is the largest city and commercial capital of Sri Lanka, historically significant as a key Indian Ocean trading hub.
  • B. Sri Jayawardenepura Kotte
    Sri Jayawardenepura Kotte is the administrative capital of Sri Lanka, located near Colombo and serving as the seat of the national legislature.
  • C. Galle
    Galle is a historic coastal city in southern Sri Lanka renowned for its well-preserved colonial-era fort and long-standing role as a key Indian Ocean trading hub.
  • D. Maharagama
    Maharagama is a suburban city in the Colombo District of Sri Lanka, known as a densely populated residential and commercial hub within the Colombo metropolitan area.
  • E. Kandy
    Kandy is a historic city in central Sri Lanka renowned for its cultural heritage, including the Temple of the Tooth and its role as a former royal stronghold.
  • 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_69bd46391c0c81909fa484446732b6a3 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd8796a420819092c1771407cd1a5d completed March 20, 2026, 5:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf339e02dc8190bb2ca6e0a0ef4621 completed March 22, 2026, 12:11 a.m.
Created at: March 20, 2026, 2:05 p.m.