Triple
T20480348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orphan stream |
E502433
|
entity |
| Predicate | hasApproximateDistanceFromSun |
P59281
|
FINISHED |
| Object | 20–50 kiloparsecs |
—
|
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: 20–50 kiloparsecs | Statement: [Orphan stream, hasApproximateDistanceFromSun, 20–50 kiloparsecs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateDistanceFromSun Context triple: [Orphan stream, hasApproximateDistanceFromSun, 20–50 kiloparsecs]
-
A.
approximateDistanceFromSun
chosen
Indicates an estimated or rough measure of how far an entity is from the Sun, rather than an exact distance.
-
B.
hasMeanDistanceFromSun
Indicates that an entity (typically a celestial body) is characterized by a specific average distance from the Sun.
-
C.
hasApproximateDistanceFromEarth
Indicates that there is an estimated or non-exact distance between an entity and Earth.
-
D.
distanceFromSunCategory
Indicates the qualitative category or range into which an entity’s distance from the Sun falls (e.g., very close, moderate, far).
-
E.
distanceFromEarth
Indicates the measured or calculated spatial separation between an entity and the planet Earth.
- 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b55d7a881909dfe3ea0e74b742b |
completed | April 20, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69e59fcdf6e08190a604204615dc56e6 |
completed | April 20, 2026, 3:38 a.m. |
Created at: April 16, 2026, 11:34 a.m.