Triple
T37340628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Audrey |
E927024
|
entity |
| Predicate | loveSong |
P19931
|
FINISHED |
| Object | Somewhere That’s Green |
—
|
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: Somewhere That’s Green | Statement: [Audrey, loveSong, Somewhere That’s Green]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loveSong Context triple: [Audrey, loveSong, Somewhere That’s Green]
-
A.
isLoveSong
chosen
Indicates that a song’s primary theme or content centers on romantic love or affectionate emotional relationships.
-
B.
favoriteSong
Indicates that one entity is the preferred or most liked song of another entity.
-
C.
hasRomanticLyrics
Indicates that the subject contains or features lyrics expressing romantic feelings, themes, or relationships.
-
D.
Love Is the Message
Indicates that the central or overriding meaning, purpose, or communication within a situation, work, or interaction is an expression or affirmation of love.
-
E.
romanticallyObsessedWith
Indicates a strong, often overwhelming romantic fixation or preoccupation that one entity has toward another.
- 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_69f76eb4e8a881908bd40da28f36fc7e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.