Triple

T7406006
Position Surface form Disambiguated ID Type / Status
Subject Lima Puluh Kota Regency E170871 entity
Predicate capital P234 FINISHED
Object Sarilamak
Sarilamak is a town in West Sumatra, Indonesia, that serves as the administrative center of Lima Puluh Kota Regency.
E662378 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: Sarilamak | Statement: [Lima Puluh Kota Regency, capital, Sarilamak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarilamak
Context triple: [Lima Puluh Kota Regency, capital, Sarilamak]
  • A. Sarigan
    Sarigan is a small, uninhabited volcanic island in the Northern Mariana Islands known for its active stratovolcano and protected wildlife habitats.
  • B. Soppeng
    Soppeng is a historical region and former kingdom in South Sulawesi, Indonesia, known for its Bugis culture and role in regional politics.
  • C. Gamosa
    Gamosa is a traditional Assamese handwoven cotton cloth, typically white with red borders and motifs, symbolizing respect, cultural identity, and social bonding in Assam.
  • D. Labasa
    Labasa is a major town in northern Fiji on the island of Vanua Levu, known as an important commercial and administrative center for the surrounding sugarcane-growing region.
  • E. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • 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: Sarilamak
Triple: [Lima Puluh Kota Regency, capital, Sarilamak]
Generated description
Sarilamak is a town in West Sumatra, Indonesia, that serves as the administrative center of Lima Puluh Kota Regency.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sarilamak
Target entity description: Sarilamak is a town in West Sumatra, Indonesia, that serves as the administrative center of Lima Puluh Kota Regency.
  • A. Sarigan
    Sarigan is a small, uninhabited volcanic island in the Northern Mariana Islands known for its active stratovolcano and protected wildlife habitats.
  • B. Soppeng
    Soppeng is a historical region and former kingdom in South Sulawesi, Indonesia, known for its Bugis culture and role in regional politics.
  • C. Gamosa
    Gamosa is a traditional Assamese handwoven cotton cloth, typically white with red borders and motifs, symbolizing respect, cultural identity, and social bonding in Assam.
  • D. Labasa
    Labasa is a major town in northern Fiji on the island of Vanua Levu, known as an important commercial and administrative center for the surrounding sugarcane-growing region.
  • E. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • 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_69c68a6010108190925e5284de022660 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f275c6e481908b4ce9ff1e418296 completed March 27, 2026, 9:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8111adbf48190a04df3cec1017b39 completed March 28, 2026, 5:34 p.m.
NEDg Description generation batch_69c81455967c81909757f42d976b535c completed March 28, 2026, 5:48 p.m.
NED2 Entity disambiguation (via description) batch_69c814b413a08190b7e5e85d73ddb430 completed March 28, 2026, 5:49 p.m.
Created at: March 27, 2026, 3:10 p.m.