Triple
T20361904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pansy Parkinson |
E496799
|
entity |
| Predicate | attitudeTowards |
P27747
|
FINISHED |
| Object | Hostile to Harry Potter |
—
|
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: Hostile to Harry Potter | Statement: [Pansy Parkinson, attitudeTowards, Hostile to Harry Potter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attitudeTowards Context triple: [Pansy Parkinson, attitudeTowards, Hostile to Harry Potter]
-
A.
attitudeToRa’y
Indicates the nature or stance of one entity’s attitude, opinion, or feeling toward Ra’y.
-
B.
cultAttitude
Indicates the stance, beliefs, or disposition that a cult or cult-like group holds toward a particular entity, idea, or practice.
-
C.
attitudeTowardLove
Indicates an entity’s feelings, beliefs, or stance regarding the concept or experience of love.
-
D.
hasUserAttitude
chosen
Indicates that one entity holds a particular attitude, opinion, or evaluative stance toward another entity or subject.
-
E.
attitudeTowardFamily
Indicates a person’s feelings, beliefs, or stance regarding their family as a whole or specific family members.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6786de5988190827584358c9db147 |
completed | April 20, 2026, 7:03 p.m. |
| PD | Predicate disambiguation | batch_69e57648be3c81908256838228cabf5c |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:25 a.m.