Triple
T36602617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rumpole’s chambers |
E902958
|
entity |
| Predicate | hasFictionalOccupant |
P196490
|
FINISHED |
| Object | Horace Rumpole |
—
|
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: Horace Rumpole | Statement: [Rumpole’s chambers, hasFictionalOccupant, Horace Rumpole]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFictionalOccupant Context triple: [Rumpole’s chambers, hasFictionalOccupant, Horace Rumpole]
-
A.
hasFictionalStaffMember
Indicates that an entity includes or employs a staff member who is a fictional character.
-
B.
hasFictionalAddressee
Indicates that an entity (such as a text or communication) is directed toward or addressed to an addressee that is fictional rather than a real person or audience.
-
C.
hasFictionalProperty
Indicates that an entity possesses a property, attribute, or characteristic that exists only in a fictional or imaginary context.
-
D.
hasNotableResidentInFiction
chosen
Indicates that a place or entity is notably associated with a fictional character who is depicted as residing there.
-
E.
hasFictionalCoStar
Indicates that one entity appears as a co-star alongside another entity within a fictional work or narrative.
- 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_69f76e66b7b88190848f7a3e1188915f |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a002962f6e081909906d6436bae6407 |
completed | May 10, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_6a00284c9c7c8190a77f18a41eee55df |
completed | May 10, 2026, 6:40 a.m. |
Created at: May 3, 2026, 4:11 p.m.