Triple
T3274652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perceval |
E68730
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Percival |
E335146
|
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: Percival | Statement: [Perceval, hasVariant, Percival]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Percival Context triple: [Perceval, hasVariant, Percival]
-
A.
Percival
Percival is the given name of British explorer Percy Fawcett, famed for his expeditions in the Amazon and the legend of the lost city of "Z."
-
B.
Percival
chosen
Percival is a knight of Arthurian legend best known for his quest for the Holy Grail and his portrayal as a pure, naive hero who matures through spiritual trials.
-
C.
Rowland
Rowland is the given name of R. H. Macy, the 19th-century American businessman who founded the Macy's department store chain.
-
D.
Bertram
Bertram is a masculine given name of Germanic origin, historically associated with nobility and later borne by various notable figures in arts, architecture, and literature.
-
E.
Galahad Threepwood
Galahad Threepwood is a roguish, hard-drinking, and charmingly irreverent member of the Blandings Castle household in P. G. Wodehouse’s comic novels, known for his colorful past and knack for getting entangled in farcical schemes.
- 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_69ad859b54f881909bf530d549caf2fd |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adaff8a440819092509bc8511b2785 |
completed | March 8, 2026, 5:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e841d5588190a53ba90a46721b0f |
completed | March 12, 2026, 4:22 p.m. |
Created at: March 8, 2026, 3:10 p.m.