Triple
T29283374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 Nashville Waffle House shooting |
E742440
|
entity |
| Predicate | suspectName |
P166117
|
FINISHED |
| Object | Travis Jeffrey Reinking |
—
|
NE NERFINISHED |
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: Travis Jeffrey Reinking | Statement: [2018 Nashville Waffle House shooting, suspectName, Travis Jeffrey Reinking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: suspectName Context triple: [2018 Nashville Waffle House shooting, suspectName, Travis Jeffrey Reinking]
-
A.
accusedName
Indicates that a particular person or entity is identified as the one who is accused in an accusation or legal charge.
-
B.
questionedCharacter
Indicates that one entity directed questions or an interrogation toward another entity.
-
C.
suspectedPerpetrator
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
D.
allegedSubject
Indicates that the referenced entity is claimed or accused to be the subject responsible for a particular action, event, or state, without confirming the truth of that claim.
-
E.
hasSuspect
chosen
Indicates that an entity is identified or considered as a suspect in relation to another entity 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_69f09121ed8c8190b4cb27be3619c262 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f66d7765208190b87b1cc6d96a151c |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 12:56 p.m.