Triple
T4705603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antony Gormley |
E104384
|
entity |
| Predicate | studiedSubject |
P36625
|
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: [Antony Gormley, studiedSubject, archaeology]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studiedSubject Context triple: [Antony Gormley, studiedSubject, archaeology]
-
A.
hasSubjectOfStudy
chosen
Indicates that an entity (such as a person or organization) focuses on, researches, or specializes in a particular field or topic of study.
-
B.
widelyStudiedIn
Indicates that something has been extensively researched, analyzed, or examined within a particular field, domain, or context.
-
C.
partOfStudy
Indicates that something is a component, segment, or subset within a larger study or research project.
-
D.
studiedBy
Indicates that a subject (such as a field, topic, or object) is examined, researched, or learned by an agent (such as a person or group).
-
E.
studiedUnder
Indicates that one entity received instruction, training, or mentorship from another, typically in an academic or apprenticeship context.
- 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_69bd43eac3c08190af7e4020c6c3704c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd650ad0f88190844bfcb46b3071c2 |
completed | March 20, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69bd621ba7448190a53ab1e2897acf71 |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:17 p.m.