Triple
T19106265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord Brett Sinclair |
E467661
|
entity |
| Predicate | screenPersonalityType |
P23367
|
FINISHED |
| Object | gentleman adventurer |
—
|
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: gentleman adventurer | Statement: [Lord Brett Sinclair, screenPersonalityType, gentleman adventurer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenPersonalityType Context triple: [Lord Brett Sinclair, screenPersonalityType, gentleman adventurer]
-
A.
personalityType
chosen
Indicates the specific psychological or behavioral profile that characterizes an entity’s typical patterns of thinking, feeling, and acting.
-
B.
성격
Indicates a relationship where one entity’s character, temperament, or personality traits are attributed to or associated with that entity.
-
C.
BigFiveMember
Indicates that an entity is a member of the group commonly referred to as the "Big Five" within a given domain (e.g., top five entities by prominence, size, or importance).
-
D.
featuresNumberOfPersonalities
Indicates that an entity is characterized by or contains a specified number of distinct personalities.
-
E.
helpsCharacterType
Indicates that one character type provides assistance or support to another character type.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e37159688190a6896d9730214ba8 |
completed | April 20, 2026, 8:27 a.m. |
| PD | Predicate disambiguation | batch_69e4b9ac41848190afd0f33b42cebe99 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:04 p.m.