Triple
T9637482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quest: The Evolution of a Scientist |
E232969
|
entity |
| Predicate | mentionsField |
P831
|
FINISHED |
| Object | theoretical physics |
—
|
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: theoretical physics | Statement: [Quest: The Evolution of a Scientist, mentionsField, theoretical physics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentionsField Context triple: [Quest: The Evolution of a Scientist, mentionsField, theoretical physics]
-
A.
mentions
chosen
Indicates that one entity refers to, cites, or brings up another entity in some form of communication or content.
-
B.
mentionedWith
Indicates that two entities are mentioned together or in close association within the same context, such as a document, sentence, or conversation.
-
C.
mentionedAs
Indicates that one entity is referred to or cited by name or description in the context of another entity.
-
D.
eraMentioned
Indicates that a specific historical or temporal era is explicitly referenced or mentioned in a given context.
-
E.
namedPersonField
Indicates that a particular data field is designated to contain a person’s name.
- 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_69ca848940cc8190b97cec654cb3bb4a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b5045cc8190ab717f42d803e010 |
completed | April 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69ccd5acfa5c8190aaba3cf548723604 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:11 p.m.