Triple
T1261803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UA1 experiment |
E12517
|
entity |
| Predicate | studiedProcess |
P23824
|
FINISHED |
| Object | proton–antiproton collisions |
—
|
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: proton–antiproton collisions | Statement: [UA1 experiment, studiedProcess, proton–antiproton collisions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studiedProcess Context triple: [UA1 experiment, studiedProcess, proton–antiproton collisions]
-
A.
studiesProcess
chosen
Indicates that an entity systematically examines, researches, or learns about a particular process.
-
B.
partOfProcess
Indicates that one event, step, or action occurs as a component or stage within a larger overall process.
-
C.
usedProcess
Indicates that an entity employed or applied a particular process to achieve a result or perform an action.
-
D.
partOfStudy
Indicates that something is a component, segment, or subset within a larger study or research project.
-
E.
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).
- 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_69a4933352e08190ac617291985e76c0 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4bfc64e648190b9c4f980eb8168aa |
completed | March 1, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69a4bb6eefbc81908dddd7d2ef368186 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:50 p.m.