Triple
T35231050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Victoria class |
E1017233
|
entity |
| Predicate | enteredServiceWithRoyalNavy |
P178340
|
FINISHED |
| Object | early 1990s |
—
|
LITERAL 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: early 1990s | Statement: [Victoria class, enteredServiceWithRoyalNavy, early 1990s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enteredServiceWithRoyalNavy Context triple: [Victoria class, enteredServiceWithRoyalNavy, early 1990s]
-
A.
enteredRoyalNavyFrontlineService
Indicates that an entity began active duty or operational deployment in the frontline forces of the Royal Navy.
-
B.
joinedRoyalNavy
Indicates that an individual entered into service as a member of the Royal Navy.
-
C.
enteredBritishService
Indicates that an entity began serving in an official capacity under British authority or institutions.
-
D.
enteredServiceInNavy
chosen
Indicates that an entity began active duty or formal service in a navy on a specified date or during a specified time period.
-
E.
statusWithRoyalNavy
Indicates the formal standing, role, or condition an entity has in relation to the Royal Navy (e.g., active service, retired, affiliated, or none).
- 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_69f76de12e4c8190bc46b71a32858356 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8cec6d48190bebfa884b2f938c0 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:02 p.m.