Triple
T5884803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Life of Pi |
E130835
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Yann Martel |
E111061
|
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: Yann Martel | Statement: [Life of Pi, author, Yann Martel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yann Martel Context triple: [Life of Pi, author, Yann Martel]
-
A.
Yann Martel
chosen
Yann Martel is a Canadian author best known for his philosophical novel "Life of Pi," which achieved international acclaim and widespread popularity.
-
B.
Markus Zusak
Markus Zusak is an Australian novelist best known for his internationally acclaimed World War II–set novel "The Book Thief."
-
C.
Paulo Coelho
Paulo Coelho is a Brazilian novelist best known for his inspirational allegorical works such as "The Alchemist," which have achieved worldwide popularity and influence.
-
D.
Vikas Swarup
Vikas Swarup is an Indian diplomat and novelist best known for his debut novel "Q & A," which was adapted into the Oscar-winning film "Slumdog Millionaire."
-
E.
Sandra Pullman
Sandra Pullman is a determined, by-the-book detective who leads a team of retired officers investigating cold cases in the British television series "New Tricks."
- 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_69c0085628dc8190b334c1b44c067efc |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0367743508190bae211e9ce8f9690 |
completed | March 22, 2026, 6:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0b13839f48190b23f22d5317eb571 |
completed | March 23, 2026, 3:19 a.m. |
Created at: March 22, 2026, 3:57 p.m.