Triple
T36878923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madison Mitchell |
E911419
|
entity |
| Predicate | isSuspectedOf |
P21177
|
FINISHED |
| Object | serial murders |
—
|
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: serial murders | Statement: [Madison Mitchell, isSuspectedOf, serial murders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSuspectedOf Context triple: [Madison Mitchell, isSuspectedOf, serial murders]
-
A.
isSuspiciousOf
Indicates that one entity believes another entity or situation may be untrustworthy, harmful, or involved in wrongdoing.
-
B.
hasSuspect
Indicates that an entity is identified or considered as a suspect in relation to another entity or incident.
-
C.
suspectedPerpetrator
chosen
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
D.
susceptibleTo
Indicates that one entity is vulnerable or likely to be affected, harmed, or influenced by another entity or factor.
-
E.
suspectedCell
Indicates that an entity is believed or suspected to be a particular cell or cell type, without confirmed verification.
- 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_69f76e82339881909607a65c0503d941 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd68f6988190abe4a5471d0876e8 |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf7890008190a8bc355ff2d61c86 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.