Triple
T3056885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington College |
E60501
|
entity |
| Predicate | hasHonorsProgram |
P38065
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Washington College, hasHonorsProgram, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHonorsProgram Context triple: [Washington College, hasHonorsProgram, yes]
-
A.
hasHonorsCollege
chosen
Indicates that an educational institution includes or is associated with an honors college program.
-
B.
isHonorSocietyFor
Indicates that an organization functions as an honor society specifically recognizing and serving the members of a particular group or field.
-
C.
hasScholarships
Indicates that an entity provides, offers, or is associated with one or more scholarships to another entity.
-
D.
graduatedWithHonors
Indicates that an entity completed an academic program with a distinction or honors-level achievement according to the institution’s criteria.
-
E.
hasStrongProgramIn
Indicates that an institution or organization offers a particularly high-quality or well-regarded program in a specified field or area.
- 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_69ad8578137c81908259dcb27c7d6d7c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ad9e13f16c81909e11ed1444c71151 |
completed | March 8, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69ad962326e081909d5521c3d3ea3158 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:02 p.m.