Triple
T19683129
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shed End |
E472642
|
entity |
| Predicate | hasNickname |
P39
|
FINISHED |
| Object | The Shed |
—
|
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: The Shed | Statement: [Shed End, hasNickname, The Shed]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Shed Context triple: [Shed End, hasNickname, The Shed]
-
A.
The Shed
The Shed is a New York City arts center known for its innovative movable structure and multidisciplinary cultural programming at Hudson Yards.
-
B.
The Shed
chosen
The Shed is the famously raucous home terrace at Dundee United’s Tannadice Park, known for its passionate atmosphere and vocal support.
-
C.
The Shed
The Shed is an interactive gallery space within Questacon that focuses on hands-on experimentation, tinkering, and creative STEM activities.
-
D.
The Loft
The Loft is a psychological thriller film produced by Gary Lucchesi about a group of married men who share a secret apartment for their affairs, only to become entangled in a murder mystery.
-
E.
M Shed
M Shed is a museum on Bristol’s harbourside that explores the city’s social, industrial, and maritime history through interactive exhibits and collections.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e641c126b88190820281058a1e7793 |
completed | April 20, 2026, 3:09 p.m. |
Created at: April 10, 2026, 1:45 p.m.