Triple
T22100625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pi Patel |
E546161
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Suraj Sharma |
—
|
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: Suraj Sharma | Statement: [Pi Patel, portrayedBy, Suraj Sharma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suraj Sharma Context triple: [Pi Patel, portrayedBy, Suraj Sharma]
-
A.
Suraj Sharma
chosen
Suraj Sharma is an Indian actor best known for his breakout performance as the shipwrecked teenager Pi Patel in Ang Lee’s acclaimed film "Life of Pi."
-
B.
Suraj Bhan
Suraj Bhan was an Indian archaeologist noted for his work on the Indus Valley Civilization, including early research at the Rakhigarhi site.
-
C.
Gokul Sharma
Gokul Sharma is an Indian cricketer known for representing Assam in domestic competitions as a key batsman and occasional off-spin bowler.
-
D.
Suraj Kanwar
Suraj Kanwar was the wife of Bhairon Singh Shekhawat, the former Vice President of India and a prominent Rajasthan politician.
-
E.
Gaurav Shukla
Gaurav Shukla is an Indian screenwriter known for his work on Hindi films, including the comedy-drama "Angrezi Medium."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1291501508190ad5689be5abb2ba6 |
completed | April 28, 2026, 9:39 p.m. |
Created at: April 16, 2026, 8:30 p.m.