Triple
T12957688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Nelson |
E310058
|
entity |
| Predicate | servedAsFlagshipOf |
P9819
|
FINISHED |
| Object | Home Fleet |
E76552
|
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: Home Fleet | Statement: [HMS Nelson, servedAsFlagshipOf, Home Fleet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Home Fleet Context triple: [HMS Nelson, servedAsFlagshipOf, Home Fleet]
-
A.
Home Fleet
chosen
The Home Fleet was the Royal Navy’s primary battle fleet, responsible for defending British home waters and serving as a key strategic force in both World Wars.
-
B.
Fleet
Fleet is a surname of English origin borne by various notable individuals, including British actor James Fleet.
-
C.
Fleet
Fleet is a town in Hampshire, England, known for its commuter links to London and surrounding areas.
-
D.
Fleet
Fleet is a lightweight, next-generation integrated development environment (IDE) by JetBrains designed for collaborative, polyglot, and remote development.
-
E.
IPC Fleetway
IPC Fleetway was a major British comics publisher and imprint known for producing influential titles in the UK comics industry.
- 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_69d7bdfb57a88190836b743e2825feca |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97e2c5bf481908ca6adcfd3354f71 |
completed | April 10, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6b8dddd80819094c80ef405024419 |
completed | May 3, 2026, 2:54 a.m. |
Created at: April 9, 2026, 5:44 p.m.