Triple
T29806182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aerial |
E756844
|
entity |
| Predicate | containsConceptSuite |
P83229
|
FINISHED |
| Object | A Sky of Honey |
—
|
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: A Sky of Honey | Statement: [Aerial, containsConceptSuite, A Sky of Honey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsConceptSuite Context triple: [Aerial, containsConceptSuite, A Sky of Honey]
-
A.
containsSuite
chosen
Indicates that one entity includes or encompasses a suite (a set or collection of related items, components, or units) as part of its contents.
-
B.
hasConcept
Indicates that an entity includes, embodies, or is associated with a particular concept.
-
C.
alsoInSuiteWith
Indicates that one entity is part of the same suite, set, or grouped collection as another entity.
-
D.
requiresConcept
Indicates that one entity depends on or needs the understanding, presence, or use of another concept in order to function, be valid, or be fully interpreted.
-
E.
hasSubConcept
Indicates that one concept is a more specific, subordinate, or narrower idea within the scope of another, more general concept.
- 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_69f2245584848190ad4cab1f07752ccb |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fec25f0fc48190b87ab1f9cd1eb0de |
completed | May 9, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69fec079a770819098df7cc3049df954 |
completed | May 9, 2026, 5:04 a.m. |
Created at: April 29, 2026, 5:21 p.m.