Triple

T26053456
Position Surface form Disambiguated ID Type / Status
Subject East Formosan E648049 entity
Predicate hasReconstructionTarget P193345 FINISHED
Object Proto–East Formosan
Proto–East Formosan is the hypothesized ancestral language from which the East Formosan branch of the Austronesian languages is reconstructed to have descended.
E1706503 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: Proto–East Formosan | Statement: [East Formosan, hasReconstructionTarget, Proto–East Formosan]
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: Proto–East Formosan
Triple: [East Formosan, hasReconstructionTarget, Proto–East Formosan]
Generated description
Proto–East Formosan is the hypothesized ancestral language from which the East Formosan branch of the Austronesian languages is reconstructed to have descended.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasReconstructionTarget
Context triple: [East Formosan, hasReconstructionTarget, Proto–East Formosan]
  • A. hasReconstructionFeature
    Indicates that something possesses a characteristic, component, or attribute specifically related to reconstruction.
  • B. hasReconstructionType
    Indicates the specific method or category of reconstruction applied to an object, structure, or dataset.
  • C. hasReconstructionPhase
    Indicates that an entity is associated with a specific phase or stage in a reconstruction process.
  • D. hasReconstructionSupportFrom
    Indicates that one entity’s reconstruction (e.g., of an object, structure, or dataset) is backed, justified, or enabled by evidence, resources, or assistance provided by another entity.
  • E. hasReconstructionLevel
    Indicates the degree or stage to which something has been rebuilt, restored, or reconstructed.
  • F. None of above. chosen

Provenance (7 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_69e77e8d419481908004e6318d28aaab completed April 21, 2026, 1:41 p.m.
NER Named-entity recognition batch_69fd44474ed48190ac372e4c88d762ed completed May 8, 2026, 2:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a111b2172988190854906f050bd658e completed May 23, 2026, 3:12 a.m.
NEDg Description generation batch_6a111bba8e5c819087fe7628a159309a completed May 23, 2026, 3:15 a.m.
NED2 Entity disambiguation (via description) batch_6a111c40813c8190b914862b78512c0f completed May 23, 2026, 3:17 a.m.
PD Predicate disambiguation batch_69fd41ef28a48190a66959be5c964461 completed May 8, 2026, 1:52 a.m.
PDg Predicate description generation batch_69fd4445f8c08190bb2dc27e0971c55d completed May 8, 2026, 2:02 a.m.
Created at: April 22, 2026, 9:11 a.m.