Triple
T368806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kure Naval Arsenal |
E8221
|
entity |
| Predicate | hadFacility |
P2836
|
FINISHED |
| Object | large dry docks |
—
|
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: large dry docks | Statement: [Kure Naval Arsenal, hadFacility, large dry docks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadFacility Context triple: [Kure Naval Arsenal, hadFacility, large dry docks]
-
A.
hasNotableFacility
Indicates that an entity possesses or hosts a facility that is of particular significance, prominence, or interest.
-
B.
hasFacilityType
chosen
Indicates that an entity possesses or is associated with a specific type or category of facility.
-
C.
ownsFacilityOn
Indicates that one entity possesses ownership or control over a facility located on or associated with another entity (such as a site, property, or area).
-
D.
hasDiscoveryFacility
Indicates that an entity has, is associated with, or is served by a facility where discoveries (such as scientific, medical, or technological findings) are made or were made.
-
E.
hasMedicalCenter
Indicates that an entity possesses, hosts, or is associated with a medical center facility.
- 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_69a2e7f2ec648190b42bc7db424f8109 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ebeab13c8190b15c2f10310ec6a8 |
completed | Feb. 28, 2026, 1:21 p.m. |
| PD | Predicate disambiguation | batch_69a2e95ede588190998fdf3a6ea90498 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.