Triple
T19298646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Dunbar |
E482633
|
entity |
| Predicate | casualtiesCombatant2 |
P1399
|
FINISHED |
| Object | several thousand killed and wounded |
—
|
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: several thousand killed and wounded | Statement: [Battle of Dunbar, casualtiesCombatant2, several thousand killed and wounded]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casualtiesCombatant2 Context triple: [Battle of Dunbar, casualtiesCombatant2, several thousand killed and wounded]
-
A.
casualties
chosen
Indicates that an event, action, or situation resulted in people being killed or injured.
-
B.
casualtiesIncluded
Indicates that the referenced count or report of casualties explicitly includes the specified individuals or groups.
-
C.
secondaryCasualtiesFrom
Indicates that an entity experiences indirect or collateral harm as a consequence of another primary event or source.
-
D.
casualtiesType
Indicates the specific category or nature of casualties (e.g., killed, injured, missing) associated with an event or incident.
-
E.
casualtiesHuman
Indicates a relationship where a human entity suffers harm, injury, or death as a result of an event, action, or situation.
- 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_69d8e8cf61b0819096fe3e4107827c4e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fc8852208190ba0337a9623d9bdf |
completed | April 20, 2026, 10:14 a.m. |
| PD | Predicate disambiguation | batch_69e4dd0bc7508190a6f9d56bd4c3404f |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:31 p.m.