Triple
T9611768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TOPS-20 |
E232117
|
entity |
| Predicate | feature |
P374
|
FINISHED |
| Object |
HELP system
The HELP system in TOPS-20 was an interactive, built-in online documentation facility that guided users through commands and system features.
|
E810938
|
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: HELP system | Statement: [TOPS-20, feature, HELP system]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HELP system Context triple: [TOPS-20, feature, HELP system]
-
A.
Help
Help is a Wikimedia Commons namespace used for pages that provide guidance and documentation on using and contributing to the media repository.
-
B.
Help
Help is a British television drama film starring Jodie Comer that explores the challenges faced by care home workers during the COVID-19 pandemic.
-
C.
Help Help
"Help Help" is a song by the American rock band The Get Up Kids from their 2002 album "On a Wire."
-
D.
Ajuda
Ajuda is a neighborhood in the city of Belém, Brazil, known for its local residential character within the metropolitan area.
-
E.
KHelpCenter
KHelpCenter is the central help and documentation viewer for the KDE desktop environment, providing users with integrated access to manuals, guides, and system help resources.
- 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: HELP system Triple: [TOPS-20, feature, HELP system]
Generated description
The HELP system in TOPS-20 was an interactive, built-in online documentation facility that guided users through commands and system features.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: HELP system Target entity description: The HELP system in TOPS-20 was an interactive, built-in online documentation facility that guided users through commands and system features.
-
A.
Help
Help is a Wikimedia Commons namespace used for pages that provide guidance and documentation on using and contributing to the media repository.
-
B.
Help
Help is a British television drama film starring Jodie Comer that explores the challenges faced by care home workers during the COVID-19 pandemic.
-
C.
Help Help
"Help Help" is a song by the American rock band The Get Up Kids from their 2002 album "On a Wire."
-
D.
Ajuda
Ajuda is a neighborhood in the city of Belém, Brazil, known for its local residential character within the metropolitan area.
-
E.
KHelpCenter
KHelpCenter is the central help and documentation viewer for the KDE desktop environment, providing users with integrated access to manuals, guides, and system help resources.
- 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_69ca8485a90c819094fe40b42fde9d70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a87764481909ab96cd2ab96d14b |
completed | April 1, 2026, 10:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d179513f9081909bcd9a456c640ba3 |
completed | April 4, 2026, 8:49 p.m. |
| NEDg | Description generation | batch_69d17b87ec6c8190a265bdbb6855dca5 |
completed | April 4, 2026, 8:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d17beebd748190b85d7bd549276197 |
completed | April 4, 2026, 9 p.m. |
Created at: March 30, 2026, 8:09 p.m.