Triple
T22975595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple "Mac vs. PC" campaign |
E571307
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object |
PC
PC is the bumbling, suit-wearing character in Apple’s “Get a Mac” ads, representing traditional Windows-based personal computers in contrast to the cooler, more capable Mac.
|
E1564200
|
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: PC | Statement: [Apple "Mac vs. PC" campaign, featuresCharacter, PC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PC Context triple: [Apple "Mac vs. PC" campaign, featuresCharacter, PC]
-
A.
PC
PC is the common abbreviation for the Peace Corps, a U.S. government volunteer program that sends Americans abroad to support social and economic development.
-
B.
PC
PC is the post-nominal abbreviation for "Privy Counsellor," denoting membership in the United Kingdom's Privy Council.
-
C.
PC
PC is the commonly used abbreviation for Pension Credit, a UK welfare benefit that provides additional income to low-income pensioners.
-
D.
PC
PC is the abbreviated name of the Committee on Political Affairs and Security, a body focused on political and security-related issues.
-
E.
PC
PC is a police constable, the entry-level rank of a police officer responsible for frontline law enforcement duties.
- 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: PC Triple: [Apple "Mac vs. PC" campaign, featuresCharacter, PC]
Generated description
PC is the bumbling, suit-wearing character in Apple’s “Get a Mac” ads, representing traditional Windows-based personal computers in contrast to the cooler, more capable Mac.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: PC Target entity description: PC is the bumbling, suit-wearing character in Apple’s “Get a Mac” ads, representing traditional Windows-based personal computers in contrast to the cooler, more capable Mac.
-
A.
PC
PC is a widely used personal computing platform that supports a broad range of software, including video games and productivity applications, across various hardware configurations.
-
B.
PC
PC is the common abbreviation for the Peace Corps, a U.S. government volunteer program that sends Americans abroad to support social and economic development.
-
C.
PC
PC is the standard abbreviation for Perfect Charity, an organization dedicated to charitable work and philanthropy.
-
D.
PC
PC is the commonly used abbreviation for Plaid Cymru, the Welsh nationalist political party advocating for Wales’s interests and greater self-governance.
-
E.
PC
PC is the post-nominal abbreviation for "Privy Counsellor," denoting membership in the United Kingdom's Privy Council.
- 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_69e245b2c6548190a0e4c7f2f7df2d48 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18235de508190ab9675d005870ff6 |
completed | April 29, 2026, 3:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bca2a23a4819084b0515313dbd2e8 |
completed | May 19, 2026, 2:25 a.m. |
| NEDg | Description generation | batch_6a0bccfc76ec8190bf03fb580f4a5b50 |
completed | May 19, 2026, 2:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bcd615d9081908b30ad2f2efcf4ea |
completed | May 19, 2026, 2:39 a.m. |
Created at: April 17, 2026, 3:48 p.m.