Triple

T5815810
Position Surface form Disambiguated ID Type / Status
Subject Battle of Kampar E128982 entity
Predicate location P40 FINISHED
Object Perak E39332 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: Perak | Statement: [Battle of Kampar, location, Perak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perak
Context triple: [Battle of Kampar, location, Perak]
  • A. Perak chosen
    Perak is a Malaysian state on the west coast of the Malay Peninsula, historically known for its rich tin deposits and former status as a key sultanate within British Malaya.
  • B. Pahang
    Pahang is a large Malaysian state on the eastern coast of Peninsular Malaysia, known for its extensive rainforests, highlands like Cameron Highlands, and long South China Sea coastline.
  • C. Kedah
    Kedah is a state in northwestern Peninsular Malaysia, historically significant as one of the oldest Malay kingdoms and once part of British Malaya.
  • D. Perlis
    Perlis is Malaysia’s smallest state, located in the northern part of the Malay Peninsula bordering Thailand and known for its agricultural landscape and quiet rural character.
  • E. Kuala Perlis
    Kuala Perlis is a small coastal town in Malaysia known as a key ferry gateway to the resort island of Langkawi.
  • 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_69c0084869e881908d7859492183ca7b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0336344148190bcf417c0b9617cb9 completed March 22, 2026, 6:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c098504c68819089eff37ea1fa0979 completed March 23, 2026, 1:33 a.m.
Created at: March 22, 2026, 3:53 p.m.