Triple
T10999190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pegasus micrometeoroid satellites |
E259961
|
entity |
| Predicate | panelArea |
P96566
|
FINISHED |
| Object | approximately 200 square meters of detection surface |
—
|
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: approximately 200 square meters of detection surface | Statement: [Pegasus micrometeoroid satellites, panelArea, approximately 200 square meters of detection surface]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: panelArea Context triple: [Pegasus micrometeoroid satellites, panelArea, approximately 200 square meters of detection surface]
-
A.
panelDivision
Indicates a relationship where a larger panel or board is divided into smaller sections or segments.
-
B.
areaComponent
Indicates that one area is a constituent or sub-area that forms part of a larger area.
-
C.
areaCControl
Indicates that an entity exercises control or authority over a specific geographic area or region.
-
D.
areaAControl
Indicates that one entity exercises control or authority over a specified area or region.
-
E.
areaBControl
Indicates that one entity has control or authority over a specific region or area labeled as B.
- 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_69d6aa8a6a548190a750f944ccdc8064 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d796d3b08c81909376cd73c42fcefe |
completed | April 9, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69d72e93ac648190b46c5d12bf3eb1e9 |
completed | April 9, 2026, 4:44 a.m. |
| PDg | Predicate description generation | batch_69d732242fdc8190be77d1f730a42935 |
completed | April 9, 2026, 4:59 a.m. |
Created at: April 8, 2026, 9:25 p.m.