Triple
T5141425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFI's 100 Years...100 Songs |
E115961
|
entity |
| Predicate | listCriteria |
P48210
|
FINISHED |
| Object | most memorable songs in American cinema |
—
|
LITERAL FINISHED |
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: most memorable songs in American cinema | Statement: [AFI's 100 Years...100 Songs, listCriteria, most memorable songs in American cinema]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: listCriteria Context triple: [AFI's 100 Years...100 Songs, listCriteria, most memorable songs in American cinema]
-
A.
listingCriterion
chosen
Indicates the rule or standard used to determine how items are selected, ordered, or displayed in a listing.
-
B.
selectionCriteria
Indicates the conditions or rules used to choose certain entities from a larger set.
-
C.
listType
Indicates that one entity specifies the classification or category type of a list associated with another entity.
-
D.
listsMeans
Indicates that one entity enumerates or specifies the meaning, definition, or interpretation of another entity.
-
E.
listedWith
Indicates that an entity is included as an item or entry within a particular list, catalog, or collection.
- 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_69bd44459a988190a772a5c2ec6a1965 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd78d7f4d081908d59adcd86f52f1d |
completed | March 20, 2026, 4:42 p.m. |
| PD | Predicate disambiguation | batch_69bd77ae2f10819098bb8939106e1281 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:43 p.m.