Triple

T14012232
Position Surface form Disambiguated ID Type / Status
Subject Weligama railway station E337110 entity
Predicate locatedIn P40 FINISHED
Object Weligama E321674 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: Weligama | Statement: [Weligama railway station, locatedIn, Weligama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Weligama
Context triple: [Weligama railway station, locatedIn, Weligama]
  • A. Weligama chosen
    Weligama is a coastal town in southern Sri Lanka known for its scenic bay, surfing spots, and traditional stilt fishing.
  • B. Hikkaduwa
    Hikkaduwa is a coastal town in southern Sri Lanka known for its beaches, coral reefs, and surf culture.
  • C. Kaduwela
    Kaduwela is a rapidly developing suburban town in Sri Lanka’s Western Province, situated near Colombo and known for its growing residential and commercial significance.
  • D. Bambalapitiya
    Bambalapitiya is a coastal suburb and prominent residential and commercial neighborhood in Colombo, Sri Lanka.
  • E. Maradana
    Maradana is a densely populated, centrally located neighborhood in Colombo, Sri Lanka, known as a major transport and educational hub of the city.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed5cfd0819085b9c860b119a9de completed April 14, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbacaa16e88190995fd86951fb54e6 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:19 p.m.