Triple
T25751008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sentinel-6 Michael Freilich |
E648467
|
entity |
| Predicate | hasTwinSatellite |
P159230
|
FINISHED |
| Object | Sentinel-6B |
—
|
NE NERFINISHED |
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: Sentinel-6B | Statement: [Sentinel-6 Michael Freilich, hasTwinSatellite, Sentinel-6B]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTwinSatellite Context triple: [Sentinel-6 Michael Freilich, hasTwinSatellite, Sentinel-6B]
-
A.
hasTwin
Indicates that one entity is a twin of another, sharing the same birth event or time with a sibling.
-
B.
hasTwinStatus
Indicates that an entity has a twin relationship or classification, such as being one of a pair of twins or having an associated twin counterpart.
-
C.
hasTwinFeature
Indicates that two entities share an identical or nearly identical feature, characteristic, or component, as if they are twins in that respect.
-
D.
isTwinWith
Indicates that two entities are twins, sharing the same birth parents and being born at (or very near) the same time.
-
E.
hasTwinSystemWith
Indicates that two systems are twins, meaning they are closely paired or mirrored counterparts in structure, function, or configuration.
- 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_69e7ab314d788190b3abe19e114080e1 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fd7ef3c48190b5f1b3b4e9cecb2b |
completed | May 2, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69f4938262ac8190b41f922d0407d272 |
completed | May 1, 2026, 11:50 a.m. |
| PDg | Predicate description generation | batch_69f497b8abb88190bb672cf6907c4b8d |
completed | May 1, 2026, 12:08 p.m. |
Created at: April 22, 2026, 4:35 a.m.