Triple
T16739838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fujikawa Maru |
E406806
|
entity |
| Predicate | hasDiveFeature |
P97817
|
FINISHED |
| Object | penetration dives into cargo holds |
—
|
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: penetration dives into cargo holds | Statement: [Fujikawa Maru, hasDiveFeature, penetration dives into cargo holds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDiveFeature Context triple: [Fujikawa Maru, hasDiveFeature, penetration dives into cargo holds]
-
A.
hasDivingComponent
Indicates that an activity, event, or process includes or involves a diving-related element or action.
-
B.
hasDiveType
Indicates that an entity performs or is associated with a specific type or category of dive.
-
C.
hasDiveSiteFeature
chosen
Indicates that a dive site possesses or includes a particular feature or characteristic.
-
D.
hasDiveDifficulty
Indicates that an action or event of diving is associated with a specified level of difficulty.
-
E.
hasDiveSite
Indicates that one entity possesses, is associated with, or provides access to a particular dive site.
- 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_69d8838ffb088190a0b11149929006bf |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e39c3d4fa48190b0db8f10a39d3ad8 |
completed | April 18, 2026, 2:59 p.m. |
| PD | Predicate disambiguation | batch_69e319c807788190901250ab6e0ca55f |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:20 a.m.