Triple
T25235050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madhan Karky |
E632314
|
entity |
| Predicate | hasWrittenDialogueFor |
P158305
|
FINISHED |
| Object | Tamil films |
—
|
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 films | Statement: [Madhan Karky, hasWrittenDialogueFor, Tamil films]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWrittenDialogueFor Context triple: [Madhan Karky, hasWrittenDialogueFor, Tamil films]
-
A.
hasDialogueIn
Indicates that an entity participates in or contains spoken or written dialogue within a specified context, such as a scene, work, or medium.
-
B.
hasDialogueTrait
Indicates that an entity possesses a specific characteristic or quality related to dialogue or conversational behavior.
-
C.
hasNoSpokenDialogue
Indicates that the referenced entity does not produce any spoken dialogue within the given context or work.
-
D.
spokenToCharacter
Indicates that one character has verbally addressed or communicated directly with another character.
-
E.
hasProseDialogue
Indicates that one entity contains or features spoken or conversational content expressed in prose form involving another entity.
- F. None of above. chosen
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_69e75a8ec5f88190b9eba06ae42b413a |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f47df84cf0819089ea6c07d67b9f01 |
completed | May 1, 2026, 10:18 a.m. |
| PD | Predicate disambiguation | batch_69f45d06d0388190b36ecde92013624a |
completed | May 1, 2026, 7:57 a.m. |
| PDg | Predicate description generation | batch_69f465699c9c8190ac7b4b32b782550c |
completed | May 1, 2026, 8:33 a.m. |
Created at: April 21, 2026, 1:06 p.m.