Triple
T15943146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Balloon Glow |
E386614
|
entity |
| Predicate | audiencePositioning |
P56401
|
FINISHED |
| Object | spectators remain on the ground around balloons |
—
|
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: spectators remain on the ground around balloons | Statement: [Balloon Glow, audiencePositioning, spectators remain on the ground around balloons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: audiencePositioning Context triple: [Balloon Glow, audiencePositioning, spectators remain on the ground around balloons]
-
A.
audienceOrientation
Indicates how something is directed, tailored, or positioned with respect to a particular audience or group of recipients.
-
B.
audienceSetting
chosen
Indicates the context or environment in which an audience is situated or addressed.
-
C.
audienceRole
Indicates the role or function an entity has as part of an audience in relation to another entity or event.
-
D.
audienceComposition
Indicates the makeup or distribution of different groups or segments within an audience in relation to something.
-
E.
audienceScale
Indicates the relative size or reach of the audience associated with an entity, event, or communication.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142d37cd88190ab50760f1783e20c |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:53 a.m.