Triple
T26486670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taiho-class aircraft carrier |
E664840
|
entity |
| Predicate | hasLeadShip |
P44837
|
FINISHED |
| Object | Japanese aircraft carrier Taiho |
—
|
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: Japanese aircraft carrier Taiho | Statement: [Taiho-class aircraft carrier, hasLeadShip, Japanese aircraft carrier Taiho]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLeadShip Context triple: [Taiho-class aircraft carrier, hasLeadShip, Japanese aircraft carrier Taiho]
-
A.
classLeadShip
chosen
Indicates a leadership relationship where one entity serves as the leading or primary representative of a class, group, or category.
-
B.
leadShip
Indicates that one entity serves as the commander or person in charge of a ship belonging to or associated with another entity.
-
C.
hasLeader
Indicates that one entity serves as the leader or head of another entity.
-
D.
statusOfLeadShip
Indicates the current condition or state assigned to the primary or leading ship in a given context or operation.
-
E.
coLeadOf
Indicates a relationship where two or more entities share joint leadership responsibility over the same project, group, or initiative.
- 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_69ee883bc85481909885f92415cbce33 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f6a8df16a88190a23820e64a3b1f92 |
completed | May 3, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69f6a751d5e48190a77dcecbe7ef9f0b |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 27, 2026, 12:31 a.m.