Triple
T22350904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cwm Gwdi |
E552523
|
entity |
| Predicate | accessTo |
P1985
|
FINISHED |
| Object | Fan y Big |
—
|
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: Fan y Big | Statement: [Cwm Gwdi, accessTo, Fan y Big]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fan y Big Context triple: [Cwm Gwdi, accessTo, Fan y Big]
-
A.
Fan y Big
chosen
Fan y Big is a prominent peak in the central Brecon Beacons of South Wales, known for its distinctive cliffs and panoramic views.
-
B.
Big Fan
Big Fan is a dark comedy-drama film about an obsessive New York Giants fan whose life unravels after a violent encounter with his favorite player.
-
C.
Mr. Big Stuff
"Mr. Big Stuff" is a popular hip-hop track by Heavy D & the Boyz known for its upbeat groove and charismatic, playful lyrics.
-
D.
Big Puma
Big Puma is the nickname of Lance Berkman, a former Major League Baseball All-Star slugger best known for his years with the Houston Astros.
-
E.
The Big Beat
The Big Beat is a 1960 hard bop jazz album by drummer Art Blakey and his Jazz Messengers, celebrated for its powerful ensemble playing and classic compositions like "Dat Dere."
- 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1579be6d8819088fed70f54ff4e66 |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:43 p.m.