Triple
T18902355
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naomi Novik |
E462366
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | League of Dragons |
—
|
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: League of Dragons | Statement: [Naomi Novik, notableWork, League of Dragons]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: League of Dragons Context triple: [Naomi Novik, notableWork, League of Dragons]
-
A.
League of Dragons
chosen
League of Dragons is a historical fantasy novel by Naomi Novik that concludes her Temeraire series, blending Napoleonic-era warfare with an alternate history of intelligent dragons.
-
B.
Les Dragons
Les Dragons is the nickname of AS Cannes, a French sports club best known for its football team.
-
C.
Land of the Dragons
Land of the Dragons is a themed area at Chessington World of Adventures featuring dragon-inspired rides, attractions, and family-friendly entertainment.
-
D.
Dragon of Dragons
Dragon of Dragons is a prestigious fantasy literature award recognizing outstanding works in the Dragonlance universe.
-
E.
Here Be Dragons
Here Be Dragons is an immersive media and virtual reality production studio known for creating innovative, story-driven experiences.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c52a4b4c8190b5821996e3c1741d |
completed | April 20, 2026, 6:18 a.m. |
Created at: April 10, 2026, 11:58 a.m.