Triple
T36187748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randyll Tarly |
E1046893
|
entity |
| Predicate | attitudeTowardSamwell |
P185008
|
FINISHED |
| Object | contemptuous |
—
|
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: contemptuous | Statement: [Randyll Tarly, attitudeTowardSamwell, contemptuous]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attitudeTowardSamwell Context triple: [Randyll Tarly, attitudeTowardSamwell, contemptuous]
-
A.
showsAttitudeTowardChivalry
Indicates that an entity expresses or demonstrates a particular stance, feeling, or evaluation regarding chivalry.
-
B.
attitudeTowardHomerSmith
Indicates the nature or quality of an entity’s feelings, opinions, or stance toward Homer Smith.
-
C.
GameOfThronesRole
Indicates that one entity plays, voices, or otherwise portrays a character in the television series "Game of Thrones" in relation to another entity.
-
D.
loyaltyAfterDaenerysDeath
Indicates that one entity remains loyal to another specifically after Daenerys’s death.
-
E.
WinterfellGodswood_associatedCharacter
Indicates that a character is associated with, connected to, or notably linked with the godswood at Winterfell.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b69b333081909cadbed3fcb8ecf5 |
completed | May 3, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c2a5f8819094ad4621d7b97e0c |
completed | May 3, 2026, 8:49 p.m. |
| PDg | Predicate description generation | batch_69f7b69a74a08190b31b1201278a2c57 |
completed | May 3, 2026, 8:56 p.m. |
Created at: May 3, 2026, 4:08 p.m.