Triple
T35580644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roma |
E1028211
|
entity |
| Predicate | casualtiesWhenSunk |
P183421
|
FINISHED |
| Object | over 1,300 killed |
—
|
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: over 1,300 killed | Statement: [Roma, casualtiesWhenSunk, over 1,300 killed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casualtiesWhenSunk Context triple: [Roma, casualtiesWhenSunk, over 1,300 killed]
-
A.
survivorsWhenSunk
Indicates that when an entity (such as a vessel) was sunk, there were survivors from that event.
-
B.
tonnageSunk
Indicates the amount of a vessel’s weight or cargo capacity that has been destroyed or sunk, typically measured in tons.
-
C.
shipSankIn
Indicates that a specific ship sank (was lost or submerged) in a particular location or body of water.
-
D.
shipsSunkOrTotalLoss
Indicates that the referenced ships were sunk or otherwise rendered a total loss (permanently unusable).
-
E.
sunkDuring
Indicates that one entity was sunk in the course of, or as a result of, the event or time period represented by another entity.
- F. None of above. chosen
Provenance (4 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_69f76e0495a081909beced418558c0b4 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79f7340e4819092a1a47f7028e63f |
completed | May 3, 2026, 7:18 p.m. |
| PD | Predicate disambiguation | batch_69f79e4bdbcc8190be7a0d2cf8a77b64 |
completed | May 3, 2026, 7:13 p.m. |
| PDg | Predicate description generation | batch_69f79ec14ce08190b22cee0b40d33743 |
completed | May 3, 2026, 7:15 p.m. |
Created at: May 3, 2026, 4:04 p.m.