Triple

T36305224
Position Surface form Disambiguated ID Type / Status
Subject Proto-Austro-Tai E893926 entity
Predicate languageFamilyScope P121065 FINISHED
Object Austro-Tai
Austro-Tai is a proposed macro-family of languages hypothesized to link the Austronesian and Tai–Kadai language families under a common ancestral origin.
 E2178482 NE FINISHED

How this triple was built (3 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: Austro-Tai | Statement: [Proto-Austro-Tai, languageFamilyScope, Austro-Tai]
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: Austro-Tai
Triple: [Proto-Austro-Tai, languageFamilyScope, Austro-Tai]
Generated description
Austro-Tai is a proposed macro-family of languages hypothesized to link the Austronesian and Tai–Kadai language families under a common ancestral origin.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: languageFamilyScope
Context triple: [Proto-Austro-Tai, languageFamilyScope, Austro-Tai]
  • A. languageFamily
    Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
  • B. languageFamilyOf
    Indicates that one entity is the language family to which the other entity (a specific language) belongs.
  • C. languageFamilyCoverage chosen
    Indicates the extent to which a given entity (such as a resource, model, or system) supports or covers the languages within a specified language family.
  • D. languageFamilyContext
    Indicates the broader linguistic family or grouping within which a particular language or linguistic element is situated.
  • E. languageFamilyAssociation
    Indicates an association where one entity belongs to, is classified under, or is related to a particular language family.
  • F. None of above.

Provenance (6 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_69f76e4c1b248190b10667d0213537fe completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a011e5a419081908d06a07b395ebd97 completed May 11, 2026, 12:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a397d867984819099f671196731feb4 completed June 22, 2026, 6:23 p.m.
NEDg Description generation batch_6a397f9cf3048190a6323f3031239176 completed June 22, 2026, 6:31 p.m.
NED2 Entity disambiguation (via description) batch_6a39835da5c48190a0cacb04de22724c completed June 22, 2026, 6:47 p.m.
PD Predicate disambiguation batch_6a011de119048190b27d361cffabc228 completed May 11, 2026, 12:08 a.m.
Created at: May 3, 2026, 4:09 p.m.