Triple
T8174849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kamiokande experiment |
E190915
|
entity |
| Predicate | usedDetectionMedium |
P25632
|
FINISHED |
| Object | ultra-pure water |
—
|
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: ultra-pure water | Statement: [Kamiokande experiment, usedDetectionMedium, ultra-pure water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedDetectionMedium Context triple: [Kamiokande experiment, usedDetectionMedium, ultra-pure water]
-
A.
usedMedium
Indicates that an action or communication was carried out through a particular medium or channel.
-
B.
usedInDetector
chosen
Indicates that something (e.g., a component, material, or method) is employed as part of a detector or detection system.
-
C.
detected
Indicates that an entity has observed, identified, or discovered the presence or occurrence of another entity or event.
-
D.
usedAgainst
Indicates that one entity is employed, applied, or deployed in opposition to, or for the purpose of affecting, another entity.
-
E.
usedOn
Indicates that one entity is applied to, operated on, or otherwise utilized in relation to another entity.
- 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb480a7ac4819088fabd5bec6ba2e5 |
completed | March 31, 2026, 4:05 a.m. |
| PD | Predicate disambiguation | batch_69cb36a7952481908f34e3e82f375a84 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:40 p.m.