Triple
T37231738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | So You Win Again |
E923151
|
entity |
| Predicate | toppedChartIn |
P155728
|
FINISHED |
| Object | UK Singles Chart |
—
|
NE NERFINISHED |
How this triple was built (2 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: UK Singles Chart | Statement: [So You Win Again, toppedChartIn, UK Singles Chart]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: toppedChartIn Context triple: [So You Win Again, toppedChartIn, UK Singles Chart]
-
A.
topHas
Indicates that one entity possesses, contains, or is associated with another entity at the highest or most general level in a hierarchy or structure.
-
B.
topper
Indicates that one entity is the highest-ranking or best-performing among a set, often in a competitive or comparative context.
-
C.
hasChartToppingHitsOn
chosen
Indicates that an entity has produced or released hits that reached the top positions on a specified music chart or ranking system.
-
D.
peakedWithinTopTenOn
Indicates that something (such as a work, product, or performance) reached a highest ranking position within the top ten on a specified chart, list, or ranking system.
-
E.
top
Indicates that one entity is physically positioned above or on the uppermost surface of another entity.
- F. None of above.
Provenance (3 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_69f76ea7f0008190b31b8e30f3d05a71 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb4134225081909fd60703b8cae397 |
completed | May 6, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69fb35bf767081908de8345358ca7f44 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.