Triple

T6334366
Position Surface form Disambiguated ID Type / Status
Subject Proto-Oceanic language E142453 entity
Predicate hasReconstructionType P70918 FINISHED
Object comparative reconstruction LITERAL FINISHED

How this triple was built (2 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: comparative reconstruction | Statement: [Proto-Oceanic language, hasReconstructionType, comparative reconstruction]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasReconstructionType
Context triple: [Proto-Oceanic language, hasReconstructionType, comparative reconstruction]
  • A. hasReconstructionStandard
    Indicates that something is associated with or governed by a specific standard or guideline for how it should be reconstructed.
  • B. hasReconstructionLevel
    Indicates the degree or stage to which something has been rebuilt, restored, or reconstructed.
  • C. containsReconstructionOf
    Indicates that one entity includes or incorporates a recreated, restored, or reconstructed version of another entity.
  • D. hasReconstructionPurpose
    Indicates that something exists or is performed with the specific aim or function of reconstruction (e.g., rebuilding, restoring, or re-creating something).
  • E. hasReconstructionMaterial
    Indicates that something is associated with, composed of, or utilizes a particular material for its reconstruction.
  • F. None of above. chosen

Provenance (4 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_69c008d4d8e88190ad301c05b08722ac completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06549084c8190b73fd94c9e0cb302 completed March 22, 2026, 9:55 p.m.
PD Predicate disambiguation batch_69c060e7e2d48190af9d004236466788 completed March 22, 2026, 9:36 p.m.
PDg Predicate description generation batch_69c064c080148190a7c3218867f1f572 completed March 22, 2026, 9:53 p.m.
Created at: March 22, 2026, 4:30 p.m.