Triple
T33811298
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roy Bland |
E866542
|
entity |
| Predicate | suspectedBy |
P166117
|
FINISHED |
| Object | George Smiley |
—
|
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: George Smiley | Statement: [Roy Bland, suspectedBy, George Smiley]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: suspectedBy Context triple: [Roy Bland, suspectedBy, George Smiley]
-
A.
isSuspiciousOf
Indicates that one entity believes another entity or situation may be untrustworthy, harmful, or involved in wrongdoing.
-
B.
hasSuspect
chosen
Indicates that an entity is identified or considered as a suspect in relation to another entity or incident.
-
C.
suspectedPerpetrator
Indicates that an entity is believed or alleged to be the person responsible for committing a particular harmful or illegal act.
-
D.
suspectedSupporter
Indicates that one entity is believed or suspected to support, assist, or be aligned with another entity, but this support is not confirmed.
-
E.
susceptibleTo
Indicates that one entity is vulnerable or likely to be affected, harmed, or influenced by another entity or factor.
- 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_69f349911a8c81908478662194b23d8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6ffcddfc08190bb83e4f2de5bee7b |
completed | May 3, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69f6fc59518081908b0275f47721d561 |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:46 a.m.