Triple
T21807989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Custer’s Last Stand |
E538396
|
entity |
| Predicate | NativeCasualtiesEstimate |
P47610
|
FINISHED |
| Object | dozens 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: dozens killed and wounded | Statement: [Custer’s Last Stand, NativeCasualtiesEstimate, dozens killed and wounded]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: NativeCasualtiesEstimate Context triple: [Custer’s Last Stand, NativeCasualtiesEstimate, dozens killed and wounded]
-
A.
militaryCasualtiesEstimate
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
B.
casualtiesEstimate
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
C.
nativeCasualties
chosen
Indicates that native or indigenous people suffered deaths or injuries as a result of a particular event, action, or conflict.
-
D.
primaryCasualtiesFrom
Indicates that an entity is the main source or cause of the casualties experienced by another entity.
-
E.
militantCasualtiesEstimate
Indicates an estimated number of militants who have been killed, wounded, or otherwise rendered casualties in a conflict or operation.
- 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f078047ca88190a0efa4bc7f2faf80 |
completed | April 28, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69e6be815a108190be81d7c987d0c0d6 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 6:53 p.m.