Triple
T31451406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chris Kyle |
E802329
|
entity |
| Predicate | numberOfClaimedKills |
P156045
|
FINISHED |
| Object | 255 |
—
|
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: 255 | Statement: [Chris Kyle, numberOfClaimedKills, 255]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfClaimedKills Context triple: [Chris Kyle, numberOfClaimedKills, 255]
-
A.
numberOfConfirmedKills
chosen
Indicates the total count of individuals that an entity is reported or confirmed to have killed.
-
B.
serviceNumberOfConfirmedKills
Indicates the number of enemy combatants an individual is officially credited with having killed in the course of their service.
-
C.
killersPerMatch
Indicates the number of kills attributed to an entity in a single match or game instance.
-
D.
numberOfVictimsClaimed
Indicates the reported count of victims associated with a particular event, incident, or action.
-
E.
numberOfPerpetratorsKilled
Indicates the count of perpetrators who were killed in the context of the described event or incident.
- 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_69f348c678ac81908a2e950867619061 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a0115fb84448190b8b67a5ace7b289a |
completed | May 10, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_6a0114ef60a081908f8db7868cf29b2f |
completed | May 10, 2026, 11:29 p.m. |
Created at: April 30, 2026, 9:13 p.m.