Triple
T36962631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Spymaster's Office |
E914346
|
entity |
| Predicate | countryOrEmpireServed |
P17699
|
FINISHED |
| Object | Empire of the Isles |
E266333
|
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: Empire of the Isles | Statement: [Royal Spymaster's Office, countryOrEmpireServed, Empire of the Isles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOrEmpireServed Context triple: [Royal Spymaster's Office, countryOrEmpireServed, Empire of the Isles]
-
A.
provinceOfEmpire
Indicates that a given province belongs to, is governed by, or forms an administrative part of a particular empire.
-
B.
governingEmpire
Indicates that one entity serves as the ruling imperial power that controls or governs another entity.
-
C.
associatedEmpire
chosen
Indicates a relationship where one entity is linked or connected to a particular empire, typically as belonging to, originating from, or being under the influence or control of that empire.
-
D.
countryRuled
Indicates that one entity exercises governing authority or political control over a country.
-
E.
hasHistoricalEmpire
Indicates that an entity once possessed, controlled, or was associated with a significant imperial power in the past.
- F. None of above.
Provenance (4 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_69f76e8c498c8190b2842db80aea8b3b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a033d975d788190aafc4be10d6c5c1c |
completed | May 12, 2026, 2:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a406370e36c819093e5d6d2b0a1a6c2 |
completed | June 27, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_6a033cc2668481908cb696e57632a68f |
completed | May 12, 2026, 2:44 p.m. |
Created at: May 3, 2026, 4:14 p.m.