Triple
T20651669
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peeves the Poltergeist |
E507509
|
entity |
| Predicate | oftenHarasses |
P107800
|
FINISHED |
| Object | first-year students |
—
|
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: first-year students | Statement: [Peeves the Poltergeist, oftenHarasses, first-year students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenHarasses Context triple: [Peeves the Poltergeist, oftenHarasses, first-year students]
-
A.
allegedHarassmentContext
Indicates the situational or circumstantial context in which an alleged act of harassment is claimed to have occurred.
-
B.
frequentlyTaunts
chosen
Indicates that one entity repeatedly mocks, provokes, or ridicules another entity on a regular or frequent basis.
-
C.
oftenSays
Indicates that one entity frequently makes a particular statement or remark, or regularly expresses a certain idea or phrase.
-
D.
oftenHave
Indicates that one entity frequently possesses, experiences, or is associated with another entity.
-
E.
oftenAttackedBy
Indicates that an entity is frequently the target of attacks carried out by another entity.
- 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_69e0b4bf58c081908e52a4500e03ff83 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af21e87c8190835bf2b2ef195626 |
completed | April 20, 2026, 10:56 p.m. |
| PD | Predicate disambiguation | batch_69e5c0315f5081908098707c6455e56e |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 11:43 a.m.