Triple
T725297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dravidian languages |
E14711
|
entity |
| Predicate | oldestAttestedLanguage |
P3921
|
FINISHED |
| Object | 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: Tamil | Statement: [Dravidian languages, oldestAttestedLanguage, Tamil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oldestAttestedLanguage Context triple: [Dravidian languages, oldestAttestedLanguage, Tamil]
-
A.
languageOfEarliestForm
Indicates the language in which the earliest known form or attested version of something (e.g., a text, name, or expression) is recorded.
-
B.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
-
C.
firstClearlyAttestedIn
chosen
Indicates the earliest known point in time or source where something is clearly documented or evidenced.
-
D.
historicalLanguage
Indicates that one language is a historical or earlier form/ancestor of another language.
-
E.
hasLinguisticHeritage
Indicates that one entity possesses or is associated with the linguistic background, tradition, or ancestry of another entity.
- 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5a7fb7c819096db848fe2ba246a |
completed | March 1, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f700cc81908c6de3eedf68433c |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.