Triple
T18772808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbig Ae/Be stars |
E459056
|
entity |
| Predicate | oftenShow |
P94008
|
FINISHED |
| Object | P Cygni profiles |
—
|
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: P Cygni profiles | Statement: [Herbig Ae/Be stars, oftenShow, P Cygni profiles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenShow Context triple: [Herbig Ae/Be stars, oftenShow, P Cygni profiles]
-
A.
oftenExhibit
chosen
Indicates that an entity frequently displays, shows, or manifests a particular property, behavior, or characteristic.
-
B.
ultimatelyShows
Indicates that something eventually reveals, demonstrates, or makes clear another thing as a final outcome or conclusion.
-
C.
oftenHave
Indicates that one entity frequently possesses, experiences, or is associated with another entity.
-
D.
showsThat
Indicates that one entity demonstrates, proves, or provides evidence for the truth or validity of another.
-
E.
oftenSoughtOn
Indicates that one entity is frequently searched for, requested, or pursued in relation to another entity.
- 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.