Triple
T28188331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KamLAND experiment |
E716234
|
entity |
| Predicate | typicalBaseline |
P12230
|
FINISHED |
| Object | about 180 km from nuclear reactors |
—
|
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: about 180 km from nuclear reactors | Statement: [KamLAND experiment, typicalBaseline, about 180 km from nuclear reactors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalBaseline Context triple: [KamLAND experiment, typicalBaseline, about 180 km from nuclear reactors]
-
A.
typicalBase
Indicates that one entity serves as the standard or most representative base or foundation for another entity in typical or common cases.
-
B.
baselineType
Indicates the type or category of a baseline used as a reference point for comparison or evaluation.
-
C.
usesBaseline
Indicates that one entity relies on or applies another entity as a reference baseline for comparison, measurement, or evaluation.
-
D.
typicalIn
chosen
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
E.
baseStandard
Indicates that one entity serves as the foundational or reference standard upon which another entity is defined, measured, or evaluated.
- 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_6a006fe981488190b4287289a3327664 |
completed | May 10, 2026, 11:45 a.m. |
| PD | Predicate disambiguation | batch_6a006f6976ec8190ba2c04fbaa946345 |
completed | May 10, 2026, 11:43 a.m. |
Created at: April 27, 2026, 10:24 p.m.