Triple
T21916358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Howard Taft |
E541191
|
entity |
| Predicate | graduatedAs |
P35205
|
FINISHED |
| Object | second in his class at Yale University |
—
|
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: second in his class at Yale University | Statement: [William Howard Taft, graduatedAs, second in his class at Yale University]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: graduatedAs Context triple: [William Howard Taft, graduatedAs, second in his class at Yale University]
-
A.
academyGraduateOf
Indicates that a person has graduated from or successfully completed a program at a particular academy.
-
B.
degreeGrantedBy
Indicates that a specific academic degree was officially conferred by a particular granting institution.
-
C.
graduatedWithHonors
Indicates that an entity completed an academic program with a distinction or honors-level achievement according to the institution’s criteria.
-
D.
graduation
Indicates that an entity has successfully completed an educational program and received a corresponding degree or qualification.
-
E.
hasRankUponGraduation
chosen
Indicates that an entity is assigned a specific rank or standing at the time of its graduation.
- 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_69e0c47c4b9c8190a5586a75f5f36453 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f123378140819090a30453c1db7f38 |
completed | April 28, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69e6be9ebf4c8190892df1a8e1313f88 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:43 p.m.