Triple
T2427641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broad Street Bullies |
E53567
|
entity |
| Predicate | mediaCoinedBy |
P33055
|
FINISHED |
| Object | Philadelphia media |
—
|
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: Philadelphia media | Statement: [Broad Street Bullies, mediaCoinedBy, Philadelphia media]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mediaCoinedBy Context triple: [Broad Street Bullies, mediaCoinedBy, Philadelphia media]
-
A.
coinedIn
Indicates that something (typically a term, phrase, or name) was first created or introduced at a particular time or in a particular place.
-
B.
mediaMarket
Indicates a relationship where a media outlet or content provider serves, targets, or operates within a particular geographic or demographic market.
-
C.
mediaAttentionLevel
Indicates the degree or intensity of attention or coverage that media outlets give to a particular subject or entity.
-
D.
coinOrPopularize
chosen
Indicates that an entity either originally creates and names a term or concept, or helps make an existing term or concept widely known and commonly used.
-
E.
mediaLanguage
Indicates the language in which a media item (such as a film, broadcast, or publication) is originally produced or presented.
- 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_69ab495c44d48190b7235b23719bc3f6 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abcc74a5108190a3a9631b0cc1a127 |
completed | March 7, 2026, 6:57 a.m. |
| PD | Predicate disambiguation | batch_69abc5aa1b60819081b87f7985c6cff3 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 6, 2026, 9:42 p.m.