Triple
T33800801
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard College class of 1907 |
E866211
|
entity |
| Predicate | hasCohortCharacteristic |
P99469
|
FINISHED |
| Object | male-only undergraduate class |
—
|
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: male-only undergraduate class | Statement: [Harvard College class of 1907, hasCohortCharacteristic, male-only undergraduate class]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCohortCharacteristic Context triple: [Harvard College class of 1907, hasCohortCharacteristic, male-only undergraduate class]
-
A.
hasSubCohort
Indicates that a cohort includes or is divided into one or more smaller, subordinate cohorts within it.
-
B.
hasCourseCharacteristic
Indicates that a course possesses or is associated with a particular characteristic, feature, or attribute.
-
C.
hasParentCohort
Indicates that one cohort is the direct parent or higher-level grouping of another cohort in a hierarchical structure.
-
D.
subjectHasCharacteristic
chosen
Indicates that a subject possesses, exhibits, or is defined by a particular characteristic or attribute.
-
E.
hasCurriculumCharacteristic
Indicates that a curriculum possesses or is defined by a specific characteristic or feature.
- 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_69f3499057fc81909d862b1309a3bd71 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037e0953908190b2930b3c06a40129 |
completed | May 12, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_6a0379f6c3308190b954f7810214ceed |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:46 a.m.