Triple
T37267227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MediaCom |
E924417
|
entity |
| Predicate | partOfBusinessCategory |
P72821
|
FINISHED |
| Object | global media agency networks |
—
|
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 media agency networks | Statement: [MediaCom, partOfBusinessCategory, global media agency networks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfBusinessCategory Context triple: [MediaCom, partOfBusinessCategory, global media agency networks]
-
A.
commercialCategory
chosen
Indicates the type of commercial classification or business category under which an entity or transaction is grouped.
-
B.
placeOfBusinessActivity
Indicates the type or nature of business activity that is conducted at a particular place or location.
-
C.
isBusinessOf
Indicates that one entity is the business, commercial concern, or enterprise associated with, owned by, or operated by another entity.
-
D.
businessBase
Indicates that one entity serves as the primary business foundation, core location, or main operational base for another entity.
-
E.
businessFunction
Indicates the specific role, activity, or operational function that an entity performs within a business context.
- 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_69f76eabd6c481909d414a80a1345c98 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a01531add1c8190b51add7bb046e2cb |
completed | May 11, 2026, 3:55 a.m. |
| PD | Predicate disambiguation | batch_6a014fef3d8c81909b509d51d0c4cdc7 |
completed | May 11, 2026, 3:41 a.m. |
Created at: May 3, 2026, 4:15 p.m.