Triple
T23514393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Case of the Perjured Parrot |
E572515
|
entity |
| Predicate | fictionalLawyer |
P152680
|
FINISHED |
| Object | Perry Mason |
—
|
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: Perry Mason | Statement: [The Case of the Perjured Parrot, fictionalLawyer, Perry Mason]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalLawyer Context triple: [The Case of the Perjured Parrot, fictionalLawyer, Perry Mason]
-
A.
legalFiction
Indicates a relationship where something is treated as true or as having a particular legal status or effect, even though it is not literally or factually the case, for the purpose of applying or interpreting the law.
-
B.
fictionalJurisdiction
Indicates that one entity has legal authority or governance over another within an invented or imaginary legal system or territory.
-
C.
fictionalPrisoner
Indicates that an entity is portrayed as a prisoner within a fictional or narrative context.
-
D.
fictionalSon
Indicates that one entity is portrayed as the son of another entity within a fictional or narrative context.
-
E.
fictionalField
Indicates that the subject is associated with a fictional or imaginary field, domain, or area rather than a real-world one.
- F. None of above. chosen
Provenance (4 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa80d9048190ab735dddd301feb4 |
completed | April 29, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
| PDg | Predicate description generation | batch_69f0bd4a0e408190ad8916faf23562d9 |
completed | April 28, 2026, 1:59 p.m. |
Created at: April 17, 2026, 6:08 p.m.