Triple
T33006359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Douglas–Belfast |
E844509
|
entity |
| Predicate | linksIslandWithMainland |
P154802
|
FINISHED |
| Object | Isle of Man |
—
|
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: Isle of Man | Statement: [Douglas–Belfast, linksIslandWithMainland, Isle of Man]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linksIslandWithMainland Context triple: [Douglas–Belfast, linksIslandWithMainland, Isle of Man]
-
A.
connectsIslandWithMainland
chosen
Indicates a relationship where a structure or route provides a direct link between an island and the mainland.
-
B.
connectedToMainlandBy
Indicates that one landmass or area is physically linked to a mainland, typically via a bridge, causeway, or other continuous connection.
-
C.
connectsPeninsulaTo
Indicates a relationship where a geographic feature or structure links a peninsula to another landmass or area.
-
D.
connectsInlandCityToCoast
Indicates a relationship where a route, link, or infrastructure connects an inland city to a coastal area or city.
-
E.
hasIslandConnection
Indicates that there exists a connection or link between entities that specifically involves or passes through an island.
- F. None of above.
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_69f3494e59f08190b9127c693e5c7e8f |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d26f27dc8190ae426a3e1573933e |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:23 a.m.