Triple
T33728217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacqueline de Bellefort |
E864202
|
entity |
| Predicate | plansMurderWith |
P169061
|
FINISHED |
| Object | Simon Doyle |
—
|
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: Simon Doyle | Statement: [Jacqueline de Bellefort, plansMurderWith, Simon Doyle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plansMurderWith Context triple: [Jacqueline de Bellefort, plansMurderWith, Simon Doyle]
-
A.
plansToMurder
chosen
Indicates that one entity intends and has formed a plan to unlawfully kill another entity.
-
B.
plansMurdersToMatch
Indicates that an entity devises murders so that they correspond to or align with another pattern, plan, or set of criteria.
-
C.
plansRobberyIn
Indicates that an entity is preparing or organizing to commit a robbery within a specified location or jurisdiction.
-
D.
plansKidnappingOf
Indicates that one entity is formulating or organizing a plan to abduct another entity against their will.
-
E.
methodOfMurderScheme
Indicates the specific method or scheme by which a murder is carried out in a given situation or plan.
- 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_69f3498a64cc8190b4b414c67b280d93 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb1b91bc8190a40733039fe939b3 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
Created at: May 1, 2026, 1:44 a.m.