Triple
T19686225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lupus |
E472717
|
entity |
| Predicate | containsNumberOfStarsWithKnownPlanets |
P64519
|
FINISHED |
| Object | several |
—
|
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: several | Statement: [Lupus, containsNumberOfStarsWithKnownPlanets, several]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsNumberOfStarsWithKnownPlanets Context triple: [Lupus, containsNumberOfStarsWithKnownPlanets, several]
-
A.
numberOfStarsWithPlanets
chosen
Indicates the count of stars that have one or more planets associated with them.
-
B.
hasNumberOfConfirmedPlanets
Indicates the relationship that specifies how many planets within a given system or context have been confirmed to exist.
-
C.
hasExoplanets
Indicates that the subject celestial system or star possesses one or more confirmed exoplanets in orbit around it.
-
D.
containsExoplanetHostStars
Indicates that the subject set or collection includes stars that are known to host one or more exoplanets.
-
E.
hasExoplanet
Indicates that an astronomical object, typically a star, possesses one or more orbiting exoplanets.
- 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6420c3f50819082b64b1fa4335e56 |
completed | April 20, 2026, 3:11 p.m. |
| PD | Predicate disambiguation | batch_69e53039ea808190a9106a53f564ab92 |
completed | April 19, 2026, 7:42 p.m. |
Created at: April 10, 2026, 1:45 p.m.