Triple
T20139445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Fuller |
E491119
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | WET Design |
—
|
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: WET Design | Statement: [Mark Fuller, employer, WET Design]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WET Design Context triple: [Mark Fuller, employer, WET Design]
-
A.
WET Design
chosen
WET Design is a renowned water feature design firm best known for creating large-scale, choreographed fountains and immersive aquatic shows around the world.
-
B.
WET
WET (Western European Time) is a standard time zone used by several Western European countries, including Portugal and the United Kingdom during winter months, corresponding to UTC+0.
-
C.
Tiwi Design
Tiwi Design is a renowned Aboriginal art centre on the Tiwi Islands known for its distinctive prints, carvings, and promotion of Tiwi culture.
-
D.
DLA Design
DLA Design is an architectural firm known for designing major public venues, including the Manchester Arena in the United Kingdom.
-
E.
Water Wizz
Water Wizz is a real-life New England water park best known for serving as the primary water park setting in the coming-of-age film "The Way Way Back."
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66798d59c81908ebcd6644b1b3744 |
completed | April 20, 2026, 5:51 p.m. |
Created at: April 11, 2026, 11:32 p.m.