Triple
T5131650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shivaram Rajguru |
E115712
|
entity |
| Predicate | roleInSaundersAssassination |
P46944
|
FINISHED |
| Object | shooter |
—
|
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: shooter | Statement: [Shivaram Rajguru, roleInSaundersAssassination, shooter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInSaundersAssassination Context triple: [Shivaram Rajguru, roleInSaundersAssassination, shooter]
-
A.
relatedAssassination
Indicates a relationship where one entity is connected to, involved in, or associated with an assassination event concerning another entity.
-
B.
assassinatedIn
Indicates that an assassination of one entity occurred within the specified location or context represented by another entity.
-
C.
roleInChappaquiddick
Indicates that an entity had a role or involvement in the Chappaquiddick incident.
-
D.
roleInCrime
chosen
Indicates the specific function, responsibility, or participation an entity has within the commission of a particular crime.
-
E.
allegedToHaveKilled
Indicates that one entity is claimed or accused, but not proven, to have killed another entity.
- 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_69bd444426bc819099ccd23f141e22aa |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7fef2e8c8190982dd67f50295ada |
completed | March 20, 2026, 5:12 p.m. |
| PD | Predicate disambiguation | batch_69bd77ac2fc48190abeebb003a82384c |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:42 p.m.