Triple
T6101969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Down on the Upside |
E136017
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Boot Camp
"Boot Camp" is a song by the American rock band Soundgarden, featured on their 1996 album *Down on the Upside*.
|
E568615
|
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: Boot Camp | Statement: [Down on the Upside, hasPart, Boot Camp]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boot Camp Context triple: [Down on the Upside, hasPart, Boot Camp]
-
A.
Weapons School
Weapons School is the United States Air Force’s elite advanced training institution that develops expert instructors in weapons and tactics for combat air forces.
-
B.
School of Access
The School of Access is an academic division at Camosun College that focuses on preparatory, upgrading, and access-oriented programs to help students transition into further education or employment.
-
C.
Upstart
Upstart is an event-based init daemon developed for Linux systems to manage services and system startup and shutdown.
-
D.
Crash Course
Crash Course is an educational YouTube series that offers fast-paced, engaging video lessons on a wide range of academic subjects.
-
E.
Jump School
Jump School is the informal name for the U.S. Army Airborne School, where soldiers are trained in military parachuting.
- 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: Boot Camp Triple: [Down on the Upside, hasPart, Boot Camp]
Generated description
"Boot Camp" is a song by the American rock band Soundgarden, featured on their 1996 album *Down on the Upside*.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Boot Camp Target entity description: "Boot Camp" is a song by the American rock band Soundgarden, featured on their 1996 album *Down on the Upside*.
-
A.
Weapons School
Weapons School is the United States Air Force’s elite advanced training institution that develops expert instructors in weapons and tactics for combat air forces.
-
B.
School of Access
The School of Access is an academic division at Camosun College that focuses on preparatory, upgrading, and access-oriented programs to help students transition into further education or employment.
-
C.
Upstart
Upstart is an event-based init daemon developed for Linux systems to manage services and system startup and shutdown.
-
D.
Crash Course
Crash Course is an educational YouTube series that offers fast-paced, engaging video lessons on a wide range of academic subjects.
-
E.
Jump School
Jump School is the informal name for the U.S. Army Airborne School, where soldiers are trained in military parachuting.
- 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_69c0087dee9881909e3655be88208c01 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05b3c073c81908248c799934d6fce |
completed | March 22, 2026, 9:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1254fbbf881908b7a3d07f0400387 |
completed | March 23, 2026, 11:34 a.m. |
| NEDg | Description generation | batch_69c125c1a230819095dd0a56309880eb |
completed | March 23, 2026, 11:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c126c8b6648190af71b450c00fd987 |
completed | March 23, 2026, 11:40 a.m. |
Created at: March 22, 2026, 4:13 p.m.