Triple
T6608393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orange Tower |
E149175
|
entity |
| Predicate | hasNeighbour |
P5707
|
FINISHED |
| Object | Dock House |
E152076
|
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: Dock House | Statement: [Orange Tower, hasNeighbour, Dock House]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dock House Context triple: [Orange Tower, hasNeighbour, Dock House]
-
A.
Dock House
chosen
Dock House is a building within the BBC’s MediaCityUK complex in Salford, used for broadcasting and production operations.
-
B.
Light House
"Light House" is an album by the indie rock band Barking at Airplanes, likely continuing their style of melodic, guitar-driven alternative music.
-
C.
The Boathouse
The Boathouse is a popular waterfront dining restaurant at Disney Springs known for its nautical theme, fresh seafood, and vintage amphicar rides.
-
D.
The Boathouse
The Boathouse is a popular lakeside restaurant and event venue in St. Louis’s Forest Park, known for its scenic views and boat rentals.
-
E.
Bridge House
Bridge House is a tiny, historic stone building famously perched over Stock Ghyll in Ambleside, England, and is one of the Lake District’s most photographed landmarks.
- 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_69c687ebc680819094caf71faba2efe2 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6af31c4748190ab5027771c9ce5b2 |
completed | March 27, 2026, 4:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6e43cc42081909762eec710773f40 |
completed | March 27, 2026, 8:10 p.m. |
Created at: March 27, 2026, 1:57 p.m.