Triple
T4160604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Röntgen radiation |
E91523
|
entity |
| Predicate | penetrationDependsOn |
P14894
|
FINISHED |
| Object | photon energy |
—
|
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: photon energy | Statement: [Röntgen radiation, penetrationDependsOn, photon energy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: penetrationDependsOn Context triple: [Röntgen radiation, penetrationDependsOn, photon energy]
-
A.
roleDependsOn
Indicates that the existence, behavior, or permissions of one role are contingent upon or derived from another role.
-
B.
hasDependency
Indicates that one entity relies on or requires another entity in order to function, exist, or be fulfilled.
-
C.
contingentOn
Indicates that the occurrence, validity, or outcome of one event or condition depends on the fulfillment or existence of another.
-
D.
powerDependsOn
chosen
Indicates that the power or effectiveness of one entity is contingent upon, or influenced by, another entity.
-
E.
areAffectedBy
Indicates that one entity experiences an effect, influence, or impact as a result of another entity or event.
- 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_69aed9626ebc8190a39de631788bea3e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0321eee88190871c1d4bf44a5007 |
completed | March 9, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69af018dc90c8190a754b1bfbc802e80 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:44 p.m.