Triple
T12976875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drag Me to Hell |
E321546
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Dileep Rao |
E180067
|
NE 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: Dileep Rao | Statement: [Drag Me to Hell, starring, Dileep Rao]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dileep Rao Context triple: [Drag Me to Hell, starring, Dileep Rao]
-
A.
Dileep Rao
chosen
Dileep Rao is an American actor known for his supporting roles in major films such as Avatar, Drag Me to Hell, and Inception.
-
B.
Ravi Basrur
Ravi Basrur is an Indian film music composer and sound designer best known for his work on high-profile Kannada films such as the K.G.F series.
-
C.
Sanjay Reddy
Sanjay Reddy is an Indian economist known for his work in development economics, poverty measurement, and global justice.
-
D.
Sanjay Suri
Sanjay Suri is an Indian actor and film producer known for his work in Hindi cinema and independent films.
-
E.
Vijay Vasudevan
Vijay Vasudevan is a computer scientist known for his work in machine learning and systems research, including co-authoring influential papers with Christian Szegedy.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d80763bd6c819094437da5b20b01d2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e48c0208190bb7ec80780480b37 |
completed | April 10, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6e266000c8190b0ba4c9e63ba0542 |
completed | May 3, 2026, 5:51 a.m. |
Created at: April 9, 2026, 8:38 p.m.