Triple

T308774
Position Surface form Disambiguated ID Type / Status
Subject Tamil E6357 entity
Predicate hasMedievalForm P4181 FINISHED
Object Middle Tamil E6357 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: Middle Tamil | Statement: [Tamil, hasMedievalForm, Middle Tamil]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Middle Tamil
Context triple: [Tamil, hasMedievalForm, Middle Tamil]
  • A. Tamil chosen
    Tamil is a classical Dravidian language spoken predominantly in the Indian state of Tamil Nadu and in parts of Sri Lanka, with a rich literary tradition spanning over two millennia.
  • B. South-Central Dravidian
    South-Central Dravidian is a branch of the Dravidian language family that includes languages such as Telugu and related tongues spoken primarily in south-central India.
  • C. Maithili
    Maithili is an Indo-Aryan language spoken primarily in the eastern Indian state of Bihar and neighboring regions, with a rich literary tradition and official recognition in India.
  • D. Sinhala
    Sinhala is an Indo-Aryan language primarily spoken by the Sinhalese people of Sri Lanka and used as one of the country’s official languages.
  • E. Old Malay
    Old Malay is an early historical form of the Malay language that served as a major lingua franca and literary language in maritime Southeast Asia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasMedievalForm
Context triple: [Tamil, hasMedievalForm, Middle Tamil]
  • A. historicalForm chosen
    Indicates that one entity is an earlier or historically attested form or variant of another entity.
  • B. hasHistoricalOrigin
    Indicates that something originated, was first established, or came into existence during a specific historical period or context.
  • C. historicallyBorneBy
    Indicates that an entity has carried, possessed, or used another entity (such as a name, title, or symbol) at some point in the past.
  • D. languageOfEarliestForm
    Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
  • E. modernFormSince
    Indicates that an entity has existed in its current or modern form starting from a specified point in time.
  • F. None of above.

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_69a2e79230508190b912ecb555aae17e completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2ea33ba688190b30d285cd7aa0d82 completed Feb. 28, 2026, 1:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3b475e91c8190b68b05a8112d35dd completed March 1, 2026, 3:37 a.m.
PD Predicate disambiguation batch_69a2e93f38308190b4b480c951f1a1c3 completed Feb. 28, 2026, 1:10 p.m.
Created at: Feb. 28, 2026, 1:06 p.m.