Triple
T5329785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Izumo-class helicopter destroyer |
E123275
|
entity |
| Predicate | secondShipCommissioned |
P47771
|
FINISHED |
| Object | 2017 |
—
|
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: 2017 | Statement: [Izumo-class helicopter destroyer, secondShipCommissioned, 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondShipCommissioned Context triple: [Izumo-class helicopter destroyer, secondShipCommissioned, 2017]
-
A.
shipCommissionedAs
Indicates that a ship entered active service under a specific name or designation at the time of its commissioning.
-
B.
firstShip
Indicates that the subject is the earliest or initial ship associated with, created by, or used in relation to the object.
-
C.
secondBoat
chosen
Indicates that one entity is the second boat in a sequence or relative ordering with respect to another boat.
-
D.
lastShip
Indicates that one entity is the final or most recent ship associated with another entity in a given sequence, context, or process.
-
E.
originalShipLaunchedIn
Indicates that an original ship was first launched in a specified year, place, or context.
- 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_69bd46477f9081909d242a327d749466 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd859552d8819080758bdd7c43c66a |
completed | March 20, 2026, 5:36 p.m. |
| PD | Predicate disambiguation | batch_69bd84583dbc819088a03e3afb30178c |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2 p.m.