Triple
T28672601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Dodd |
E725768
|
entity |
| Predicate | identifiedThrough |
P107472
|
FINISHED |
| Object | psychic visions |
—
|
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: psychic visions | Statement: [Frank Dodd, identifiedThrough, psychic visions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: identifiedThrough Context triple: [Frank Dodd, identifiedThrough, psychic visions]
-
A.
identifiedIn
Indicates that an entity is recognized, discovered, or documented within a specified source, context, or location.
-
B.
identifiedUsing
chosen
Indicates that one entity was recognized, distinguished, or determined by means of a specified method, tool, or identifier.
-
C.
identified
Indicates that one entity has recognized, named, or established the identity of another entity.
-
D.
identifierFor
Indicates that one entity serves as a unique identifying label or code for another entity.
-
E.
recognizedThrough
Indicates that something becomes known, identified, or acknowledged by means of a particular method, medium, or process.
- 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6617ba4a88190bfc5c305acb4f93f |
completed | May 2, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 5:04 a.m.