Triple

T22408607
Position Surface form Disambiguated ID Type / Status
Subject Mattakkuliya E553939 entity
Predicate adjacentTo P224 FINISHED
Object Modara NE NERFINISHED

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: Modara | Statement: [Mattakkuliya, adjacentTo, Modara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Modara
Context triple: [Mattakkuliya, adjacentTo, Modara]
  • A. Modara chosen
    Modara is a coastal urban neighborhood in Colombo, Sri Lanka, known for its port-adjacent location and dense residential and commercial activity.
  • B. Modon
    Modon is a historic port city in southwestern Greece, known today as Methoni, that served as a strategic Venetian stronghold and battleground in late medieval and early modern conflicts.
  • C. Drasna
    Drasna is a Dragon-type specialist who serves as one of the Elite Four members in the Kalos region of the Pokémon series.
  • D. Tynaarlo
    Tynaarlo is a municipality in the northeastern Netherlands known for its rural character and location between the cities of Groningen and Assen.
  • E. Shandar
    Shandar was a French avant-garde record label known for releasing experimental and free jazz recordings in the 1970s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4e6ce8819085a1e06d886bf21c completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158badc008190a3f5afb520a25e5f completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.