Triple
T10007104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elvis Costello |
E198279
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object | Alison |
E719766
|
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: Alison | Statement: [Elvis Costello, notableSong, Alison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alison Context triple: [Elvis Costello, notableSong, Alison]
-
A.
Alison
Alison is a feminine given name of English origin, commonly used in many English-speaking countries.
-
B.
Alison
chosen
Alison is a central character in Alan Garner's supernatural novel "The Owl Service," whose experiences drive the story's exploration of Welsh myth and identity.
-
C.
Alison Grace
Alison Grace is a film editor best known for her work on the family sports movie "Air Bud."
-
D.
Allison
Allison is a common English-language surname of Scottish and Irish origin, often derived from "son of Alice" or "son of Alan."
-
E.
Annalise
Annalise is a minor but pivotal character in John le Carré’s espionage novel "Smiley’s People," involved in the intricate web of intelligence and personal relationships surrounding George Smiley.
- 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_69ca830fcca48190bbbd9b20c233835f |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd16afb481909a5d5893e024683f |
completed | April 2, 2026, 1:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d26a5d7e088190b5b1a852bfdc9073 |
completed | April 5, 2026, 1:57 p.m. |
Created at: March 30, 2026, 8:52 p.m.