Triple
T2171864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS LST-393 |
E48442
|
entity |
| Predicate | homeportDuringService |
P3150
|
FINISHED |
| Object | various U.S. Navy bases |
—
|
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: various U.S. Navy bases | Statement: [USS LST-393, homeportDuringService, various U.S. Navy bases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeportDuringService Context triple: [USS LST-393, homeportDuringService, various U.S. Navy bases]
-
A.
homeportDuringWar
Indicates that an entity served as the designated home port or primary base for another entity during a period of war.
-
B.
homePort
chosen
Indicates that a vessel or mobile entity is based at, registered to, or primarily operates from a particular port or harbor.
-
C.
mooredAt
Indicates that one object, typically a vessel or floating structure, is secured or anchored at a specific location or facility.
-
D.
stateOfHarbor
Indicates the current operational or physical condition or status of a harbor.
-
E.
hasResearchVesselsHomeport
Indicates that a location serves as the primary homeport or base of operations for one or more research vessels.
- 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_69a88aa3faa48190995b233af6525815 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc1559ff481908efe3f214b2570dc |
completed | March 7, 2026, 6:10 a.m. |
| PD | Predicate disambiguation | batch_69abbd9efc1c81909a65044a1ffc9038 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:45 p.m.