Triple
T38498293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HD 186408 |
E919754
|
entity |
| Predicate | hasWideBinarySeparationWith |
P56529
|
FINISHED |
| Object | HD 186427 |
—
|
NE NERFINISHED |
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: HD 186427 | Statement: [HD 186408, hasWideBinarySeparationWith, HD 186427]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWideBinarySeparationWith Context triple: [HD 186408, hasWideBinarySeparationWith, HD 186427]
-
A.
hasBinaryPeriod
Indicates that two objects in a binary system have a specific orbital period for completing one full revolution around their common center of mass.
-
B.
hasBinary
chosen
Indicates that one entity is associated with another entity in a binary (two-component) relationship, typically as one of the two members of a pair.
-
C.
isBinary
Indicates that the related entity or value has exactly two possible states, options, or components.
-
D.
hasCompanionSeparation
Indicates that one entity is separated or kept apart from its companion or associated counterpart.
-
E.
hasWideBodyVariant
Indicates that an entity has a corresponding wide-body version or variant of itself.
- 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_69f76e9ddd4481908f8c04439d848f9d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:31 p.m.