Triple
T12312026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard MacDuff |
E293501
|
entity |
| Predicate | relationshipWithDirkGently |
P38921
|
FINISHED |
| Object | friend |
—
|
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: friend | Statement: [Richard MacDuff, relationshipWithDirkGently, friend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipWithDirkGently Context triple: [Richard MacDuff, relationshipWithDirkGently, friend]
-
A.
relationshipToDrWatson
Indicates the specific personal or professional relationship an entity has with Dr. Watson.
-
B.
associatedWithDirectorCharacter
Indicates a relationship where something is linked to or connected with a director character, typically signifying involvement, relevance, or attribution to that director character.
-
C.
relationshipToCharacter
chosen
Indicates the specific type of personal, social, or narrative connection that one entity has to a given character.
-
D.
relationshipToBertieWooster
Indicates the specific type of personal or social relationship an entity has with Bertie Wooster.
-
E.
relationshipWithSybilFawlty
Indicates the type or nature of a relationship that an entity has with Sybil Fawlty.
- 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_69d6ab6a2b50819082f6aedd32ed608a |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f621570819091ee1db2609233ea |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ec02c008190a56aae60a3d9eff6 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:53 p.m.