Triple
T25704992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atterbury Plot |
E644562
|
entity |
| Predicate | conspiredTo |
P112937
|
FINISHED |
| Object | seize the Tower of London |
—
|
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: seize the Tower of London | Statement: [Atterbury Plot, conspiredTo, seize the Tower of London]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conspiredTo Context triple: [Atterbury Plot, conspiredTo, seize the Tower of London]
-
A.
conspirator
Indicates that an entity participates with others in planning or carrying out a secret or illicit scheme or action.
-
B.
conspiracy
chosen
Indicates a secret agreement or collaboration between multiple entities to plan or carry out an unlawful, deceptive, or harmful act.
-
C.
metConspiratorsAt
Indicates that an individual met with one or more co-conspirators at a specific place and/or time as part of a conspiracy.
-
D.
hasApproximateNumberOfConspirators
Indicates that an entity is associated with an estimated or approximate count of conspirators involved with it.
-
E.
complicitIn
Indicates involvement in or knowing participation in a wrongful, illegal, or unethical act carried out by another party.
- 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_69e77e83c8ec8190bf52fcdac4838984 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fc1052508190bee01272205a9f70 |
completed | May 2, 2026, 1:28 p.m. |
| PD | Predicate disambiguation | batch_69f4a0f7c6008190ae8cee3e71e19b94 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 9:02 p.m.