Triple
T19450914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caffè Macs cafeteria |
E486610
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object |
Caffe Macs
Caffe Macs is Apple Inc.’s in-house cafeteria system, known for serving employees a wide variety of high-quality meals at its corporate campuses.
|
E1376413
|
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: Caffe Macs | Statement: [Caffè Macs cafeteria, hasAlternativeName, Caffe Macs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caffe Macs Context triple: [Caffè Macs cafeteria, hasAlternativeName, Caffe Macs]
-
A.
Caffe
Caffe is an open-source deep learning framework known for its speed and modular design, widely used in computer vision research and applications.
-
B.
McCafé
McCafé is McDonald's in-house coffeehouse-style chain offering specialty coffee drinks, pastries, and café-style food items.
-
C.
Café Lab
Café Lab is a café-style social and collaborative space within Knowledge Capital, designed to foster interaction, creativity, and idea exchange among visitors.
-
D.
MocaccinoOS
MocaccinoOS is a Linux distribution that evolved from the Sabayon project, focusing on modern container-based and image-based system management.
-
E.
CAFE
CAFE is a U.S. regulatory program that sets mandatory fuel efficiency standards for cars and light trucks to reduce energy consumption and emissions.
- 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: Caffe Macs Triple: [Caffè Macs cafeteria, hasAlternativeName, Caffe Macs]
Generated description
Caffe Macs is Apple Inc.’s in-house cafeteria system, known for serving employees a wide variety of high-quality meals at its corporate campuses.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Caffe Macs Target entity description: Caffe Macs is Apple Inc.’s in-house cafeteria system, known for serving employees a wide variety of high-quality meals at its corporate campuses.
-
A.
Caffe
Caffe is an open-source deep learning framework known for its speed and modular design, widely used in computer vision research and applications.
-
B.
McCafé
McCafé is McDonald's in-house coffeehouse-style chain offering specialty coffee drinks, pastries, and café-style food items.
-
C.
Café Lab
Café Lab is a café-style social and collaborative space within Knowledge Capital, designed to foster interaction, creativity, and idea exchange among visitors.
-
D.
MocaccinoOS
MocaccinoOS is a Linux distribution that evolved from the Sabayon project, focusing on modern container-based and image-based system management.
-
E.
CAFE
CAFE is a U.S. regulatory program that sets mandatory fuel efficiency standards for cars and light trucks to reduce energy consumption and emissions.
- 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_69d8e8d7ad488190a3373045029b0f3b |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6338db7c081908793f23592ebef6b |
completed | April 20, 2026, 2:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a073b3175248190817aedbfd95927dc |
completed | May 15, 2026, 3:26 p.m. |
| NEDg | Description generation | batch_6a073be7e28c8190999dacec37a2f3b4 |
completed | May 15, 2026, 3:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a073c9461d08190a2b89ebd16e66a58 |
completed | May 15, 2026, 3:32 p.m. |
Created at: April 10, 2026, 1:38 p.m.