Triple
T29494104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Royal Sovereign (05) |
E748167
|
entity |
| Predicate | SovietName |
P133852
|
FINISHED |
| Object | Arkhangelsk |
—
|
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: Arkhangelsk | Statement: [HMS Royal Sovereign (05), SovietName, Arkhangelsk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SovietName Context triple: [HMS Royal Sovereign (05), SovietName, Arkhangelsk]
-
A.
sovietPeriodName
Indicates that the object is the name used for the subject during the Soviet period.
-
B.
citySovietName
Indicates that a city has or had an official or commonly used name during the Soviet era.
-
C.
nameInSovietService
chosen
Indicates that an entity bore or used a particular name specifically during its period of service in the Soviet Union or under Soviet authority.
-
D.
hasSovietLeaderParticipant
Indicates that a Soviet leader is a participant in the referenced event, action, or relationship.
-
E.
SovietDesignation
Indicates that an entity has been assigned an official designation or code name by Soviet authorities or according to Soviet classification systems.
- 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_69f0bd448c6881908aa6b475cefd5ddc |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c0cd4c08190b3e2f87522299a0d |
completed | May 2, 2026, 9:26 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 4:17 p.m.