Triple
T19261725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UY Scuti |
E481663
|
entity |
| Predicate | hasLuminosityRange |
P85778
|
FINISHED |
| Object | ~3×10^5–5×10^5 solar luminosities |
—
|
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: ~3×10^5–5×10^5 solar luminosities | Statement: [UY Scuti, hasLuminosityRange, ~3×10^5–5×10^5 solar luminosities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLuminosityRange Context triple: [UY Scuti, hasLuminosityRange, ~3×10^5–5×10^5 solar luminosities]
-
A.
luminanceRange
chosen
Indicates the span between the minimum and maximum luminance (brightness) values associated with an entity or visual element.
-
B.
luminescenceCapability
Indicates the ability of an entity to emit light through luminescence.
-
C.
hasLumen
Indicates that one entity possesses or is characterized by a specific luminous intensity or light output measured in lumens.
-
D.
hasColorRange
Indicates that an entity possesses or is associated with a specific span or set of colors, rather than a single discrete color.
-
E.
hasVariableBrightness
Indicates that the brightness of an entity is not constant but changes over time or under different conditions.
- 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_69d8e8ce54cc8190998418ff1f66ef28 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fb8a022c8190b313e9d11d38e482 |
completed | April 20, 2026, 10:10 a.m. |
| PD | Predicate disambiguation | batch_69e4dd07a7208190afcd51ba1dc87c33 |
completed | April 19, 2026, 1:47 p.m. |
Created at: April 10, 2026, 1:28 p.m.