Triple
T3972556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saliva |
E92366
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Always |
E217059
|
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: Always | Statement: [Saliva, notableWork, Always]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Always Context triple: [Saliva, notableWork, Always]
-
A.
Always
"Always" is a 1989 romantic fantasy film directed by Steven Spielberg, starring Richard Dreyfuss as a deceased pilot who returns as a spirit to guide his former lover and a young aviator.
-
B.
Always
"Always" is a popular romantic song written by American composer Irving Berlin in 1925, often remembered as a classic standard of early 20th-century American music.
-
C.
Always
chosen
"Always" is a power ballad by American rock band Bon Jovi, released in 1994 and known as one of their biggest global hits.
-
D.
Always
Always is a Procter & Gamble feminine hygiene brand best known for its sanitary pads and menstrual care products.
-
E.
Sempre sempre
"Sempre sempre" is a popular Italian song performed by Romina Power (with Al Bano), known as one of the duo’s signature romantic hits.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed96624188190ac8c45bb57ab72b5 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef996ff6c8190ba8cc490e4744b95 |
completed | March 9, 2026, 4:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5400fa9ac8190adf70a4c49eac32c |
completed | March 14, 2026, 11:01 a.m. |
Created at: March 9, 2026, 3:32 p.m.