Triple

T22121023
Position Surface form Disambiguated ID Type / Status
Subject Kampar E546665 entity
Predicate locatedNear P294 FINISHED
Object Tapah
Tapah is a town in the state of Perak, Malaysia, known as a local administrative and transport hub in the Kinta Valley region.
 E1519745 NE FINISHED

How this triple was built (4 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: Tapah | Statement: [Kampar, locatedNear, Tapah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tapah
Context triple: [Kampar, locatedNear, Tapah]
  • A. Tapul
    Tapul is a small island municipality in the province of Sulu in the southern Philippines.
  • B. Tapini
    Tapini is a small highland town in Papua New Guinea known as the administrative center of the Goilala District in Central Province.
  • C. Ko Tapu
    Ko Tapu is a tall, narrow limestone islet in Thailand famously known as "James Bond Island" for its appearance in the film *The Man with the Golden Gun*.
  • D. Paya
    Paya is a small settlement located within Panama’s Darién Province, known for its remote jungle environment and proximity to the Darién Gap.
  • E. Paya
    Paya is an indigenous language of Honduras, also known as Pech, spoken by the Pech people of northeastern Honduras.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tapah
Triple: [Kampar, locatedNear, Tapah]
Generated description
Tapah is a town in the state of Perak, Malaysia, known as a local administrative and transport hub in the Kinta Valley region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tapah
Target entity description: Tapah is a town in the state of Perak, Malaysia, known as a local administrative and transport hub in the Kinta Valley region.
  • A. Tapul
    Tapul is a small island municipality in the province of Sulu in the southern Philippines.
  • B. Tapini
    Tapini is a small highland town in Papua New Guinea known as the administrative center of the Goilala District in Central Province.
  • C. Ko Tapu
    Ko Tapu is a tall, narrow limestone islet in Thailand famously known as "James Bond Island" for its appearance in the film *The Man with the Golden Gun*.
  • D. Paya
    Paya is an indigenous language of Honduras, also known as Pech, spoken by the Pech people of northeastern Honduras.
  • E. Paya
    Paya is a small settlement located within Panama’s Darién Province, known for its remote jungle environment and proximity to the Darién Gap.
  • F. None of above. chosen

Provenance (5 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_69e11e38b3848190ac3a4fa97d56e65a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12951fcd48190841319cd879c15cb completed April 28, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a8f1fee748190be30339887981f99 completed May 18, 2026, 4:01 a.m.
NEDg Description generation batch_6a0a924f9c0081909e33d6900675495b completed May 18, 2026, 4:15 a.m.
NED2 Entity disambiguation (via description) batch_6a0a92f3ac948190893088711a300610 completed May 18, 2026, 4:17 a.m.
Created at: April 16, 2026, 8:31 p.m.