Triple
T7854862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese carrier Zuiho |
E182147
|
entity |
| Predicate | laidDownYear |
P10132
|
FINISHED |
| Object | 1934 |
—
|
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: 1934 | Statement: [Japanese carrier Zuiho, laidDownYear, 1934]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laidDownYear Context triple: [Japanese carrier Zuiho, laidDownYear, 1934]
-
A.
laidDownEndYear
Indicates the year in which something that was previously established, enacted, or laid down (such as a rule, law, or policy) ceased to be in effect.
-
B.
depositionYear
Indicates the calendar year in which something (such as a document, sample, or item) was formally deposited or submitted.
-
C.
laidDownDate
chosen
Indicates the date on which something (such as a rule, law, standard, or foundation) was formally established, set, or put in place.
-
D.
deploymentYear
Indicates the calendar year in which an entity (such as a system, product, or resource) was first put into active use or operation.
-
E.
landingYear
Indicates the year in which a landing event (such as an arrival or touchdown) took place.
- 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_69ca82869ee08190b8f9040dbc2c0467 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb1a72cfdc8190a3186c4c2894f571 |
completed | March 31, 2026, 12:50 a.m. |
| PD | Predicate disambiguation | batch_69cae92180f88190ae3d44c3de7adc93 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:51 p.m.