Triple
T34190891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mutsu |
E877104
|
entity |
| Predicate | scrapping |
P95852
|
FINISHED |
| Object | partial salvage after sinking |
—
|
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: partial salvage after sinking | Statement: [Mutsu, scrapping, partial salvage after sinking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scrapping Context triple: [Mutsu, scrapping, partial salvage after sinking]
-
A.
scrappingStatus
chosen
Indicates the current state or outcome of a scrapping process applied to an entity (e.g., whether it has been scrapped, is pending scrapping, or not scrapped).
-
B.
scrapedBy
Indicates that something has been obtained or collected from a source through a scraping process, typically by an automated tool or agent.
-
C.
scrappingPeriod
Indicates the time span during which something is being discarded, decommissioned, or removed from use.
-
D.
scrappingLocation
Indicates the place where an object or material is dismantled, discarded, or processed for scrapping.
-
E.
scrappingReason
Indicates the reason or justification for discarding or scrapping an item, asset, or entity from use.
- 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_69f349af20a4819089ac24d28f2d8112 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f710240640819087919759ec52e4bd |
completed | May 3, 2026, 9:06 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:55 a.m.