Triple
T2413020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snapchat |
E52237
|
entity |
| Predicate | hasFeature |
P182
|
FINISHED |
| Object |
Discover
Discover is Snapchat’s curated content platform that showcases stories, news, and entertainment from publishers, creators, and brands.
|
E264024
|
NE FINISHED |
How this triple was built (4 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: Discover | Statement: [Snapchat, hasFeature, Discover]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Discover Context triple: [Snapchat, hasFeature, Discover]
-
A.
Discover
Discover is a major U.S.-based financial services company best known for its Discover credit card network and related banking products.
-
B.
Discovery
Discovery is a NASA Space Shuttle orbiter best known for deploying the Hubble Space Telescope and flying numerous key missions in the Space Shuttle program.
-
C.
Discovery
Discovery is a global media brand best known for its non-fiction television programming focused on science, exploration, nature, and real-life entertainment.
-
D.
Discovery
Discovery was an English exploration ship most notably used by Henry Hudson during his early 17th-century voyages in search of a Northwest Passage.
-
E.
Discovery
Discovery is a Toronto International Film Festival program that showcases emerging filmmakers and debut or early-career feature films from around the world.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Discover Triple: [Snapchat, hasFeature, Discover]
Generated description
Discover is Snapchat’s curated content platform that showcases stories, news, and entertainment from publishers, creators, and brands.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Discover Target entity description: Discover is Snapchat’s curated content platform that showcases stories, news, and entertainment from publishers, creators, and brands.
-
A.
Discover
Discover is a major U.S.-based financial services company best known for its Discover credit card network and related banking products.
-
B.
Discovery
Discovery is a NASA Space Shuttle orbiter best known for deploying the Hubble Space Telescope and flying numerous key missions in the Space Shuttle program.
-
C.
Discovery
Discovery is a global media brand best known for its non-fiction television programming focused on science, exploration, nature, and real-life entertainment.
-
D.
Discovery
Discovery was an English exploration ship most notably used by Henry Hudson during his early 17th-century voyages in search of a Northwest Passage.
-
E.
Discovery
Discovery is a Toronto International Film Festival program that showcases emerging filmmakers and debut or early-career feature films from around the world.
- F. None of above. chosen
Provenance (5 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_69ab495622948190bc6bc6e4cddaf645 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc92a4e1c8190819fa676295ac145 |
completed | March 7, 2026, 6:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aeb3f00cc481909c2841a6f2ebadad |
completed | March 9, 2026, 11:50 a.m. |
| NEDg | Description generation | batch_69aeb630b9588190a09652e9a3e65731 |
completed | March 9, 2026, 11:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69aeb68465608190b40e8be870b54ffb |
completed | March 9, 2026, 12:01 p.m. |
Created at: March 6, 2026, 9:41 p.m.