Triple
T10398625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jason Dunham |
E245084
|
entity |
| Predicate | actOfBravery |
P36130
|
FINISHED |
| Object | covered a live grenade with his helmet and body to protect fellow Marines |
—
|
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: covered a live grenade with his helmet and body to protect fellow Marines | Statement: [Jason Dunham, actOfBravery, covered a live grenade with his helmet and body to protect fellow Marines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: actOfBravery Context triple: [Jason Dunham, actOfBravery, covered a live grenade with his helmet and body to protect fellow Marines]
-
A.
typeOfBravery
Indicates a specific kind or category of bravery that characterizes an entity’s courageous behavior or action.
-
B.
describesGallantryOf
Indicates a relationship where one entity characterizes, explains, or details the gallant or brave behavior of another entity.
-
C.
notableDeed
chosen
Indicates that an entity is recognized for performing a significant or noteworthy action or achievement.
-
D.
usedMeansToRescue
Indicates that one entity employed a particular method, tool, or means in order to carry out a rescue.
-
E.
campaignHonours
Indicates that an entity has received formal recognition or awards for its participation in a specific campaign.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9d1f2408190beaa8197641c66b4 |
completed | April 7, 2026, 11:26 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb438c481908dff87c47de2f069 |
completed | April 7, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:07 p.m.