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.