Triple
T18772791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbig Ae/Be stars |
E459056
|
entity |
| Predicate | showInfraredExcess |
P29858
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Herbig Ae/Be stars, showInfraredExcess, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: showInfraredExcess Context triple: [Herbig Ae/Be stars, showInfraredExcess, true]
-
A.
infraredExcess
chosen
Indicates that an object emits more infrared radiation than expected from its visible or thermal continuum, typically due to additional dust or circumstellar material.
-
B.
numberOfInfraredChannels
Indicates the count of distinct infrared channels associated with or supported by an entity.
-
C.
visibleInLongExposureImages
Indicates that the subject can be detected or seen when images are captured using long exposure photography settings.
-
D.
supportsInfraredConnectivity
Indicates that one entity provides or enables infrared-based communication or data transfer capabilities for another entity.
-
E.
hasColorExcess
Indicates that an entity exhibits a measured amount of color excess, typically representing the difference between its observed color and its intrinsic or expected color.
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e593378a4081909cc1b0856fce7d7d |
completed | April 20, 2026, 2:45 a.m. |
| PD | Predicate disambiguation | batch_69e48d1126e4819099607837ed5aadca |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:52 a.m.