Triple
T20896503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Outlook |
E514550
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Outlook Bridge |
—
|
NE NERFINISHED |
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: Outlook Bridge | Statement: [Outlook, hasLandmark, Outlook Bridge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Outlook Bridge Context triple: [Outlook, hasLandmark, Outlook Bridge]
-
A.
Outlook Traveller
Outlook Traveller is an Indian travel magazine known for its in-depth destination features, travel guides, and photography.
-
B.
Outlook
Outlook is Microsoft’s email and personal information management application that provides integrated email, calendar, contacts, and task functionality for individuals and organizations.
-
C.
Outlook
chosen
Outlook is a small town in Saskatchewan, Canada, known for its location along the South Saskatchewan River and its nearby agricultural and irrigation infrastructure.
-
D.
Outlook
Outlook is an opinion and analysis section of The Washington Post featuring commentary, essays, and in-depth perspectives on current events and issues.
-
E.
Exchange
"Exchange" is a popular R&B song by American singer Bryson Tiller, known for its smooth production, emotional lyrics, and significant role in boosting his mainstream success.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d062f26c81908d99d6a9d3b99604 |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 12:47 p.m.