Triple
T32459379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony Bennett and Lady Gaga |
E829522
|
entity |
| Predicate | firstCollaborationSong |
P200297
|
FINISHED |
| Object | The Lady Is a Tramp |
E66288
|
NE 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: The Lady Is a Tramp | Statement: [Tony Bennett and Lady Gaga, firstCollaborationSong, The Lady Is a Tramp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstCollaborationSong Context triple: [Tony Bennett and Lady Gaga, firstCollaborationSong, The Lady Is a Tramp]
-
A.
firstSong
Indicates that one song is the earliest or initial song in a specified sequence, collection, or context.
-
B.
lastCollaborativeAlbum
Indicates that one entity is the most recent album created jointly by the other entity and at least one collaborator.
-
C.
firstMajorDuetRecordingBy
chosen
Indicates that the object is the first major duet recording created or released by the subject.
-
D.
firstCollaborationYear
Indicates the calendar year in which two or more entities collaborated with each other for the first time.
-
E.
firstAlbumWith
Indicates that two or more entities share the same first album, or that one entity’s first album was created or released together with another specified entity.
- F. None of above.
Provenance (4 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_69f3491df9288190afc0b23b1d6e72ce |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a037c894b488190bcbec2eccaff4a01 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a34704c76f881909aa1c9aa49a98a8f |
completed | June 18, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_6a0379edf2d88190b492fca86ed23cac |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 12:57 a.m.