Triple
T37919008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ralphie Tennelli |
E945902
|
entity |
| Predicate | classmatesWith |
P49703
|
FINISHED |
| Object | Arnold Perlstein |
—
|
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: Arnold Perlstein | Statement: [Ralphie Tennelli, classmatesWith, Arnold Perlstein]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: classmatesWith Context triple: [Ralphie Tennelli, classmatesWith, Arnold Perlstein]
-
A.
oneOfFewFriendlyClassmatesOf
Indicates that the subject is among a small number of classmates who are friendly toward the object.
-
B.
hasClassmate
chosen
Indicates that two people attend the same class or course, making them classmates.
-
C.
graduationClass
Indicates the specific graduating cohort or class year with which an entity (such as a student or alumnus) is associated.
-
D.
collegeTeammateOf
Indicates that two individuals were teammates on the same college sports team.
-
E.
studentsCombine
Indicates that multiple students join together or pool their efforts, resources, or attributes into a single combined entity or group.
- 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_69f76ef2ebd88190be5229f2621070b3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fd19f791f48190bbb6f6047f9ddc59 |
completed | May 7, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69fd0df365948190bc9bfc7ffd46acd8 |
completed | May 7, 2026, 10:10 p.m. |
Created at: May 3, 2026, 4:20 p.m.