Triple
T9458164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lilac Fairy |
E228070
|
entity |
| Predicate | guides |
P488
|
FINISHED |
| Object | Prince Désiré |
E228068
|
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: Prince Désiré | Statement: [Lilac Fairy, guides, Prince Désiré]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prince Désiré Context triple: [Lilac Fairy, guides, Prince Désiré]
-
A.
Prince Désiré
chosen
Prince Désiré is the fairy-tale prince who awakens the enchanted princess in "The Sleeping Beauty" and embodies the story’s ideal of heroic, romantic love.
-
B.
Louis Duchosal
Louis Duchosal was a notable Swiss operatic tenor of the mid-20th century, recognized for his performances in major European opera houses.
-
C.
Lunice Fermin Pierre II
Lunice Fermin Pierre II is a Canadian DJ and electronic music producer known for his innovative trap-influenced sound and as one half of the duo TNGHT.
-
D.
Célestin Faustin
Célestin Faustin was a prominent Haitian naïve painter known for his vivid, imaginative works that reflect Haiti’s cultural and spiritual life.
-
E.
Henri de Castries
Henri de Castries is a French businessman best known for serving as chairman and CEO of the global insurance group AXA.
- 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_69ca843b123881909b0e60028475d12d |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7f924f3081909dd937cbe6802881 |
completed | April 1, 2026, 8:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d12ce01b548190a30f6cc7f3084b06 |
completed | April 4, 2026, 3:23 p.m. |
Created at: March 30, 2026, 7:52 p.m.