Triple
T29336078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aishwarya Rai as Sana |
E743908
|
entity |
| Predicate | romanticGenreElementIn |
P170425
|
FINISHED |
| Object | Enthiran |
—
|
NE NERFINISHED |
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: Enthiran | Statement: [Aishwarya Rai as Sana, romanticGenreElementIn, Enthiran]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanticGenreElementIn Context triple: [Aishwarya Rai as Sana, romanticGenreElementIn, Enthiran]
-
A.
romanceType
Indicates the specific kind or category of romantic relationship that exists between the related entities.
-
B.
romanticLeadIn
Indicates that one entity is the primary romantic interest or central romantic partner of another within a narrative or context.
-
C.
romanticArc
Indicates a developing or ongoing romantic relationship or storyline between the involved entities.
-
D.
romanticThemeExpressedThrough
Indicates that a romantic theme is conveyed or manifested through a particular medium, element, or aspect of a work or situation.
-
E.
romanticTragedy
Indicates a relationship where a romantic involvement between entities leads to or is characterized by tragic or sorrowful outcomes.
- 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_69f09126cfcc8190899b16fbf3c2bf7b |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f69063edbc81909e7735954aabee0b |
completed | May 3, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
| PDg | Predicate description generation | batch_69f68f6584a88190a8c4d95c0c84bee9 |
completed | May 2, 2026, 11:57 p.m. |
Created at: April 28, 2026, 1:31 p.m.