Triple
T28136825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Piccadilly Circus advertising screens |
E714229
|
entity |
| Predicate | typicalAdvertisers |
P23729
|
FINISHED |
| Object | global consumer brands |
—
|
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: global consumer brands | Statement: [Piccadilly Circus advertising screens, typicalAdvertisers, global consumer brands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalAdvertisers Context triple: [Piccadilly Circus advertising screens, typicalAdvertisers, global consumer brands]
-
A.
typicalAffiliates
Indicates that one entity is commonly or characteristically associated, aligned, or partnered with another entity.
-
B.
adType
Indicates the classification or category of an advertisement associated with an entity or event.
-
C.
advertises
chosen
Indicates that one entity promotes, publicizes, or markets another entity, typically to attract attention or customers.
-
D.
advertisingPractice
Indicates a relationship where an entity engages in or is associated with the activity, methods, or strategies of advertising.
-
E.
usedAdvertisements
Indicates that an entity has employed or displayed specific advertisements for promotion or communication purposes.
- 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_69efd6af156c81908f50c2cd7db0e1ef |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_6a0067cde0f08190b2cd93af5f00d519 |
completed | May 10, 2026, 11:11 a.m. |
| PD | Predicate disambiguation | batch_6a0065820c8c8190994734433c64a30a |
completed | May 10, 2026, 11:01 a.m. |
Created at: April 27, 2026, 9:50 p.m.