Triple
T28570559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | "She's in Love with the Boy" |
E722802
|
entity |
| Predicate | sideAOrLeadTrackOfSingle |
P102128
|
FINISHED |
| Object | "She's in Love with the Boy" single |
—
|
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: "She's in Love with the Boy" single | Statement: ["She's in Love with the Boy", sideAOrLeadTrackOfSingle, "She's in Love with the Boy" single]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sideAOrLeadTrackOfSingle Context triple: ["She's in Love with the Boy", sideAOrLeadTrackOfSingle, "She's in Love with the Boy" single]
-
A.
side1Track
Indicates that an entity is associated with or belongs to the first side or track in a two-sided or multi-track configuration.
-
B.
isLeadTrackOf
chosen
Indicates that a track serves as the primary or featured track associated with a particular release, album, or recording project.
-
C.
sideThreeTrack
Indicates that an entity is associated with, or corresponds to, the third side (or track) in a multi-sided or multi-track context.
-
D.
singleAorBside
Indicates that exactly one of the two related entities is on side A or side B, but not both simultaneously.
-
E.
sideOneTrackListOrder
Indicates the ordering or sequence position of tracks on the first side of a multi-sided recording or medium.
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f650924b1c8190978fca7cb865f32a |
completed | May 2, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 4:09 a.m.