Triple
T11704786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RollerCoaster Tycoon |
E278209
|
entity |
| Predicate | availableOn |
P1278
|
FINISHED |
| Object |
PC
PC is a widely used personal computing platform that runs general-purpose software, including games like RollerCoaster Tycoon.
|
E388051
|
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: [RollerCoaster Tycoon, availableOn, PC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PC Context triple: [RollerCoaster Tycoon, availableOn, 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 the standard abbreviation for Perfect Charity, an organization dedicated to charitable work and philanthropy.
- 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: [RollerCoaster Tycoon, availableOn, PC]
Generated description
PC is a widely used personal computing platform that runs general-purpose software, including games like RollerCoaster Tycoon.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: PC Target entity description: PC is a widely used personal computing platform that runs general-purpose software, including games like RollerCoaster Tycoon.
-
A.
PC
chosen
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 commonly used abbreviation for Pension Credit, a UK welfare benefit that provides additional income to low-income pensioners.
-
D.
PC
PC is the standard abbreviation for Perfect Charity, an organization dedicated to charitable work and philanthropy.
-
E.
PC
PC is the common abbreviation for the Progressive Conservative Party of Canada, a former major centre-right political party that played a significant role in Canadian federal politics throughout the 20th century.
- F. None of above.
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_69d6aaff2ce88190b4a1e4b341ad5377 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a49c8c38819083d83f5fdec52b7f |
completed | April 10, 2026, 7:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef83525ae081909ee6f3fbb5d37dd7 |
completed | April 27, 2026, 3:40 p.m. |
| NEDg | Description generation | batch_69ef9b673120819097b542bb9a8f8bdb |
completed | April 27, 2026, 5:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69efd683366881909dd9621e7c57d0be |
completed | April 27, 2026, 9:34 p.m. |
Created at: April 8, 2026, 9:40 p.m.