Triple

T1938908
Position Surface form Disambiguated ID Type / Status
Subject Mon-Khmer E41506 entity
Predicate hasSubfamily P747 FINISHED
Object Pearic
Pearic is a small branch of Austroasiatic languages spoken by indigenous Pearic peoples in parts of Cambodia and Thailand.
 E216898 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: Pearic | Statement: [Mon-Khmer, hasSubfamily, Pearic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pearic
Context triple: [Mon-Khmer, hasSubfamily, Pearic]
  • A. Hoyte
    Hoyte is the first name of Hoyte van Hoytema, a renowned Dutch-Swedish cinematographer known for his work on major films such as "Interstellar" and "Dunkirk."
  • B. Lontzen
    Lontzen is a municipality in eastern Belgium, located in the country’s German-speaking region near the border with Germany.
  • C. Owaneco
    Owaneco was a prominent Mohegan sachem (chief) known for his leadership and land dealings in colonial New England during the late 17th and early 18th centuries.
  • D. Pearce
    Pearce is a surname and given name of English origin, commonly considered a variant of "Pierce" and ultimately derived from the name "Peter."
  • E. Parlick
    Parlick is a prominent hill in Lancashire, England, popular with walkers and paragliders and known for its sweeping views over the Forest of Bowland.
  • 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: Pearic
Triple: [Mon-Khmer, hasSubfamily, Pearic]
Generated description
Pearic is a small branch of Austroasiatic languages spoken by indigenous Pearic peoples in parts of Cambodia and Thailand.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pearic
Target entity description: Pearic is a small branch of Austroasiatic languages spoken by indigenous Pearic peoples in parts of Cambodia and Thailand.
  • A. Hoyte
    Hoyte is the first name of Hoyte van Hoytema, a renowned Dutch-Swedish cinematographer known for his work on major films such as "Interstellar" and "Dunkirk."
  • B. Lontzen
    Lontzen is a municipality in eastern Belgium, located in the country’s German-speaking region near the border with Germany.
  • C. Owaneco
    Owaneco was a prominent Mohegan sachem (chief) known for his leadership and land dealings in colonial New England during the late 17th and early 18th centuries.
  • D. Pearce
    Pearce is a surname and given name of English origin, commonly considered a variant of "Pierce" and ultimately derived from the name "Peter."
  • E. Parlick
    Parlick is a prominent hill in Lancashire, England, popular with walkers and paragliders and known for its sweeping views over the Forest of Bowland.
  • 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_69a88649b24c819080047f26b6db2ded completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb2c8be648190836580cec77a143f completed March 7, 2026, 5:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3f81e0c819090e3f2154215ff18 completed March 8, 2026, 10:11 p.m.
NEDg Description generation batch_69adf4e94b5081909d4010612d81b917 completed March 8, 2026, 10:15 p.m.
NED2 Entity disambiguation (via description) batch_69adf60463d88190896cedb2b45a67ed completed March 8, 2026, 10:19 p.m.
Created at: March 4, 2026, 7:36 p.m.