Triple
T23894928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Geller |
E600876
|
entity |
| Predicate | roleAtSchool |
P121011
|
FINISHED |
| Object | student |
—
|
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: student | Statement: [Paris Geller, roleAtSchool, student]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleAtSchool Context triple: [Paris Geller, roleAtSchool, student]
-
A.
schoolRole
chosen
Indicates the specific function, position, or capacity an entity holds within a school context (e.g., student, teacher, administrator).
-
B.
schoolBelongsTo
Indicates that a particular school is owned by, affiliated with, or under the authority or jurisdiction of a specific organization, institution, or administrative entity.
-
C.
courseRole
Indicates the specific function or position an individual holds within a course, such as student, instructor, or assistant.
-
D.
schoolRoll
Indicates the official list or record of students enrolled in a particular school or class.
-
E.
publicSchool
Indicates that an educational institution is operated and funded by a government or public authority rather than by private entities.
- 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_69e295341ac0819080647f2908af793c |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cdd857d081908740c4abb246c2ba |
completed | April 29, 2026, 9:22 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:25 p.m.