Triple
T36412921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gadding with Ghouls |
E896928
|
entity |
| Predicate | teacherWhoAssigned |
P52943
|
FINISHED |
| Object | Gilderoy Lockhart |
—
|
NE NERFINISHED |
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: Gilderoy Lockhart | Statement: [Gadding with Ghouls, teacherWhoAssigned, Gilderoy Lockhart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teacherWhoAssigned Context triple: [Gadding with Ghouls, teacherWhoAssigned, Gilderoy Lockhart]
-
A.
hasTeacher
chosen
Indicates that one entity serves as an instructor or educator for another entity.
-
B.
previousTeacher
Indicates that one entity formerly served as a teacher or instructor of the other entity in the past.
-
C.
teacherInScene
Indicates that an entity is acting in the role of a teacher within a particular scene or context.
-
D.
traditionallyTaughtBy
Indicates that something is customarily or historically instructed or passed down by a particular person, group, or institution.
-
E.
teacherOrInfluence
Indicates that one entity serves as a teacher to, or has a significant influence on the development, behavior, or thinking of, 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_69f76e54ce408190849acc3f7758937c |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bcccd7988190aa5c931ff347d33c |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.