Triple
T27102097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marshall College |
E686467
|
entity |
| Predicate | fictionalDisciplineTaught |
P98445
|
FINISHED |
| Object | archaeology |
—
|
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: archaeology | Statement: [Marshall College, fictionalDisciplineTaught, archaeology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fictionalDisciplineTaught Context triple: [Marshall College, fictionalDisciplineTaught, archaeology]
-
A.
fictionalEducation
Indicates that one entity has an educational background, training, or schooling that exists only within a fictional or imaginary context relative to another entity.
-
B.
setInFictionalUniversity
Indicates that the events or narrative take place within the setting of a fictional university.
-
C.
teachingSubject
chosen
Indicates that an entity is engaged in teaching or instructing another entity in a particular subject or field of knowledge.
-
D.
isTaughtTo
Indicates that some knowledge, skill, or subject is being instructed or conveyed by a teacher or source to a learner or recipient.
-
E.
hasFictionalSpecialization
Indicates that an entity’s area of focus, expertise, or role is within a fictional or imaginative domain rather than a real-world specialization.
- 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_69ef1489f8b481908e24a1985982bd26 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f6cee45590819086e489bfccbe4ac3 |
completed | May 3, 2026, 4:28 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1188708190b8f0f56e595e6057 |
completed | May 3, 2026, 4:16 a.m. |
Created at: April 27, 2026, 8:48 a.m.