Triple

T308773
Position Surface form Disambiguated ID Type / Status
Subject Tamil E6357 entity
Predicate hasAncientForm P4181 FINISHED
Object Old Tamil 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: Old Tamil | Statement: [Tamil, hasAncientForm, Old Tamil]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasAncientForm
Context triple: [Tamil, hasAncientForm, Old Tamil]
  • A. hasHistoricalOrigin
    Indicates that something originated, was first established, or came into existence during a specific historical period or context.
  • B. languageOfEarliestForm
    Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
  • C. historicalForm chosen
    Indicates that one entity is an earlier or historically attested form or variant of another entity.
  • D. hasHistoricalPrecursor
    Indicates that one entity existed earlier and served as a predecessor, model, or influential forerunner to the other in a historical context.
  • E. hasCognate
    Indicates that two linguistic forms in different languages share a common historical origin, typically descending from the same ancestral word.
  • F. None of above.

Provenance (3 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_69a2e79230508190b912ecb555aae17e completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2ea33ba688190b30d285cd7aa0d82 completed Feb. 28, 2026, 1:14 p.m.
PD Predicate disambiguation batch_69a2e93f38308190b4b480c951f1a1c3 completed Feb. 28, 2026, 1:10 p.m.
Created at: Feb. 28, 2026, 1:06 p.m.