Triple
T7918935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unity (Node 1) |
E183894
|
entity |
| Predicate | powerInterface |
P79769
|
FINISHED |
| Object | distributes power between ISS segments |
—
|
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: distributes power between ISS segments | Statement: [Unity (Node 1), powerInterface, distributes power between ISS segments]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerInterface Context triple: [Unity (Node 1), powerInterface, distributes power between ISS segments]
-
A.
inPower
Indicates that one entity currently holds governing authority, control, or leadership over a group, organization, or domain.
-
B.
powerDependsOn
Indicates that the power or effectiveness of one entity is contingent upon, or influenced by, another entity.
-
C.
powerChange
Indicates a change in the level, amount, or state of power associated with an entity over time.
-
D.
powerScope
Indicates the extent or domain within which an entity’s power, authority, or influence is valid or can be exercised.
-
E.
powerOption
Indicates that one entity provides or specifies a particular power-related configuration or choice available to another entity.
- F. None of above. chosen
Provenance (4 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a9173548190a04889726f7b251f |
completed | March 31, 2026, 3:08 a.m. |
| PD | Predicate disambiguation | batch_69cae9316e98819080be7bf1a6ff92f1 |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf7882b048190baa333af9f698590 |
completed | March 30, 2026, 10:22 p.m. |
Created at: March 30, 2026, 5:05 p.m.