Triple
T23514373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Case of the Lame Canary |
E572514
|
entity |
| Predicate | hasSecretaryCharacter |
P61558
|
FINISHED |
| Object | Della Street |
—
|
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: Della Street | Statement: [The Case of the Lame Canary, hasSecretaryCharacter, Della Street]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSecretaryCharacter Context triple: [The Case of the Lame Canary, hasSecretaryCharacter, Della Street]
-
A.
hasHumanCharacterRole
Indicates that an entity is assigned a role or function specifically associated with a human character within a context such as a story, performance, or representation.
-
B.
hasOfficialCharacter
Indicates that something possesses an authorized, formal, or legally recognized status or role within an official context.
-
C.
hasFounderCharacter
Indicates that an entity has a founder who possesses a specified character trait or set of personal qualities.
-
D.
hasFictionalStaffMember
chosen
Indicates that an entity includes or employs a staff member who is a fictional character.
-
E.
hasFictionalSpokesperson
Indicates that an entity is represented or promoted by a spokesperson who is a fictional or imaginary character.
- 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_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. |
Created at: April 17, 2026, 6:08 p.m.