Triple
T25277494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louise Banks |
E633738
|
entity |
| Predicate | educationSpecialization |
P48900
|
FINISHED |
| Object | comparative linguistics |
—
|
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: comparative linguistics | Statement: [Louise Banks, educationSpecialization, comparative linguistics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: educationSpecialization Context triple: [Louise Banks, educationSpecialization, comparative linguistics]
-
A.
subjectSpecialization
Indicates that one subject focuses on, or has expertise in, a particular field, topic, or area of knowledge.
-
B.
educationField
chosen
Indicates the academic or professional discipline in which an entity has been educated or trained.
-
C.
institutionSpecialization
Indicates that an institution focuses on, is dedicated to, or has expertise in a particular field, domain, or area of activity.
-
D.
educationalField
Indicates the academic or disciplinary area in which an educational activity, program, or qualification is focused.
-
E.
educationAspiration
Indicates an individual's intended or desired level of education or educational achievement.
- 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_69e75a9402fc81909362ca85277c06d9 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f55e519978819087a1676564a74630 |
completed | May 2, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f4a0edd10c81908a052ab864d57c54 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 1:18 p.m.