Triple
T29211036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jivaka |
E740545
|
entity |
| Predicate | workMeterContext |
P4875
|
FINISHED |
| Object | Tamil prosody |
—
|
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 prosody | Statement: [Jivaka, workMeterContext, Tamil prosody]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workMeterContext Context triple: [Jivaka, workMeterContext, Tamil prosody]
-
A.
originalWorkMeter
Indicates that a work’s measurement or metrical structure is derived from or corresponds to that of an original source work.
-
B.
hasMeter
chosen
Indicates that one entity possesses, uses, or is associated with a specific meter (a measuring device or metrical pattern).
-
C.
laborContext
Indicates the labor-related circumstances, conditions, or setting within which an action, relationship, or event takes place.
-
D.
workAttributedContext
Indicates that a work is associated with or derived from a particular contextual source, setting, or circumstance that informs its creation or interpretation.
-
E.
materialWorked
Indicates that an agent performs work or processing on a specified material.
- 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_69f07cba2f808190a2746477d4e8345b |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f664057f888190b8c7e45431970680 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 12:11 p.m.