Triple
T19977098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levels |
E493719
|
entity |
| Predicate | precedes |
P97
|
FINISHED |
| Object |
Silhouettes
Silhouettes is a level in the game "Levels" known for its distinctive shadow-themed visuals and gameplay challenges.
|
E1403925
|
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: Silhouettes | Statement: [Levels, precedes, Silhouettes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Silhouettes Context triple: [Levels, precedes, Silhouettes]
-
A.
Silhouettes
"Silhouettes" is a melodic progressive house track by Swedish DJ and producer Avicii, known for its uplifting sound and inspirational lyrics about personal growth and change.
-
B.
Silhouettes
"Silhouettes" is a popular 1960s pop song recorded by the British band Herman's Hermits, known for its catchy melody and romantic lyrics.
-
C.
Silhouettes
Silhouettes is a collection of fin-de-siècle poetry by Arthur Symons that helped establish his reputation as a leading figure in English Symbolism and Decadent literature.
-
D.
Silhouette
"Silhouette" is a smooth jazz album by saxophonist Kenny G, known for its mellow, melodic sound and commercial success in the late 1980s.
-
E.
Two Silhouettes
Two Silhouettes is an animated ballet sequence from Disney’s 1946 anthology film Make Mine Music, featuring rotoscoped dancers set against stylized, romantic backdrops.
- 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: Silhouettes Triple: [Levels, precedes, Silhouettes]
Generated description
Silhouettes is a level in the game "Levels" known for its distinctive shadow-themed visuals and gameplay challenges.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Silhouettes Target entity description: Silhouettes is a level in the game "Levels" known for its distinctive shadow-themed visuals and gameplay challenges.
-
A.
Silhouettes
"Silhouettes" is a popular 1960s pop song recorded by the British band Herman's Hermits, known for its catchy melody and romantic lyrics.
-
B.
Silhouettes
"Silhouettes" is a melodic progressive house track by Swedish DJ and producer Avicii, known for its uplifting sound and inspirational lyrics about personal growth and change.
-
C.
Silhouettes
Silhouettes is a collection of fin-de-siècle poetry by Arthur Symons that helped establish his reputation as a leading figure in English Symbolism and Decadent literature.
-
D.
Silhouette
"Silhouette" is a smooth jazz album by saxophonist Kenny G, known for its mellow, melodic sound and commercial success in the late 1980s.
-
E.
Two Silhouettes
Two Silhouettes is an animated ballet sequence from Disney’s 1946 anthology film Make Mine Music, featuring rotoscoped dancers set against stylized, romantic backdrops.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d1054e08190993b92b86ec5bbc8 |
completed | April 20, 2026, 5:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07fdd9ccd081909bc8555dfab586b7 |
completed | May 16, 2026, 5:17 a.m. |
| NEDg | Description generation | batch_6a07feea266c81909da71d549a8857d3 |
completed | May 16, 2026, 5:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07ff598550819093b6303a88dfefd2 |
completed | May 16, 2026, 5:23 a.m. |
Created at: April 11, 2026, 3:27 p.m.