Triple
T5995041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welsh Grand National |
E133445
|
entity |
| Predicate | sponsoredBy |
P67
|
FINISHED |
| Object | Coral |
E364762
|
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: Coral | Statement: [Welsh Grand National, sponsoredBy, Coral]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Coral Context triple: [Welsh Grand National, sponsoredBy, Coral]
-
A.
Coral
chosen
Coral is a major UK-based betting and gaming company known for its nationwide chain of bookmakers and online gambling services.
-
B.
Black Coral
"Black Coral" is a rock song by the Stills-Young Band, the short-lived collaboration between Stephen Stills and Neil Young in the mid-1970s.
-
C.
Kinda Coral
Kinda Coral is a soft, pastel pinkish-orange color variant used as one of the signature finishes for Google’s Pixel 6 smartphone.
-
D.
Supercoralli
Supercoralli is a prominent literary fiction series by the Italian publisher Einaudi, known for showcasing acclaimed contemporary and classic authors.
-
E.
Green Seas
Green Seas is an episode of the BBC nature documentary series Blue Planet II that explores the rich biodiversity and ecological dynamics of coastal and shallow marine environments.
- 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_69c00870ddbc81909880fa3864f4f38d |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04e943dcc8190a09817e8ef0e4188 |
completed | March 22, 2026, 8:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1086f6b5481908c573c6e533ad98a |
completed | March 23, 2026, 9:31 a.m. |
Created at: March 22, 2026, 4:05 p.m.