Triple
T19914825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shardik |
E478638
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Richard Adams |
—
|
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: Richard Adams | Statement: [Shardik, author, Richard Adams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Adams Context triple: [Shardik, author, Richard Adams]
-
A.
Richard Adams
chosen
Richard Adams was an English novelist best known for his classic animal fantasy novel "Watership Down."
-
B.
Richard Adams
Richard Adams is a fictional television news cameraman in the 1979 nuclear-accident thriller film "The China Syndrome."
-
C.
Peter S. Beagle
Peter S. Beagle is an American fantasy author and screenwriter best known for writing the novel "The Last Unicorn" and contributing to various fantasy film and television projects.
-
D.
Kenneth Grahame
Kenneth Grahame was a British writer best known for his classic children’s novel "The Wind in the Willows," which has inspired numerous adaptations in literature and film.
-
E.
Dick King-Smith
Dick King-Smith was a British children's author best known for his animal-themed novels, including "The Sheep-Pig," which inspired the film "Babe."
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6599394f081909246006c2e83bacc |
completed | April 20, 2026, 4:51 p.m. |
Created at: April 10, 2026, 1:53 p.m.