Triple

T23529992
Position Surface form Disambiguated ID Type / Status
Subject Philippine linguistic area E576536 entity
Predicate hasSuperordinate P1244 FINISHED
Object Austronesian linguistic area
The Austronesian linguistic area is a broad region encompassing the diverse but historically related languages of the Austronesian family, stretching from Madagascar through Island Southeast Asia into the Pacific.
E1592304 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: Austronesian linguistic area | Statement: [Philippine linguistic area, hasSuperordinate, Austronesian linguistic area]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Austronesian linguistic area
Context triple: [Philippine linguistic area, hasSuperordinate, Austronesian linguistic area]
  • A. Indo-Pacific linguistic area
    The Indo-Pacific linguistic area is a proposed macro-area encompassing diverse, often non-Austronesian languages of the Indian and Pacific Ocean regions that are hypothesized to share deep historical connections and structural features.
  • B. Southeast Asia linguistic area
    The Southeast Asia linguistic area is a region where languages from diverse families have converged to share common structural features such as tonal systems, analytic grammar, and similar word order due to long-term contact and diffusion.
  • C. Polynesian linguistic area
    The Polynesian linguistic area is a group of closely related Oceanic languages spoken across the Polynesian islands, characterized by shared phonological, grammatical, and lexical features resulting from common ancestry and long-term contact.
  • D. Austronesian languages
    Austronesian languages are a large and widely dispersed language family spoken across maritime Southeast Asia, Madagascar, the Pacific Islands, and parts of mainland Asia.
  • E. Austronesian cultural sphere
    The Austronesian cultural sphere is a broad maritime-based cultural and linguistic region spanning Island Southeast Asia and the Pacific, characterized by related Austronesian languages, seafaring traditions, and shared ancestral cultural practices.
  • 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: Austronesian linguistic area
Triple: [Philippine linguistic area, hasSuperordinate, Austronesian linguistic area]
Generated description
The Austronesian linguistic area is a broad region encompassing the diverse but historically related languages of the Austronesian family, stretching from Madagascar through Island Southeast Asia into the Pacific.

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_69e245f5a8848190a2ba42e271c6c31f completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1ac7646a48190b5dcbaf8c0c194df completed April 29, 2026, 7 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0cdf53c66c819087f1e9481dcfc8ee completed May 19, 2026, 10:08 p.m.
NEDg Description generation batch_6a0ce4602a408190b4357d98cf16477a completed May 19, 2026, 10:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0d721bdae08190a06f48a6073c5351 completed May 20, 2026, 8:34 a.m.
Created at: April 17, 2026, 6:09 p.m.