Triple
T23894927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Geller |
E600876
|
entity |
| Predicate | worksOnSchoolNewspaperWith |
P121024
|
FINISHED |
| Object | Rory Gilmore |
—
|
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: Rory Gilmore | Statement: [Paris Geller, worksOnSchoolNewspaperWith, Rory Gilmore]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksOnSchoolNewspaperWith Context triple: [Paris Geller, worksOnSchoolNewspaperWith, Rory Gilmore]
-
A.
studentNewspaper
Indicates a relationship where an entity is the student-run newspaper associated with a particular school, college, or university.
-
B.
associatedWithNewspaper
chosen
Indicates a relationship where an entity is connected or linked to a newspaper, such as through ownership, employment, contribution, or representation.
-
C.
youthNewspaper
Indicates that an entity is a newspaper specifically intended for or associated with young people or youth audiences.
-
D.
isServedByNewspaper
Indicates that a person or entity receives news or information provided by a particular newspaper.
-
E.
journalismSchool
Indicates that one entity is a journalism school attended by, affiliated with, or providing education/training in journalism to the other 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_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.