Triple
T9427303
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Willow (song) |
E227288
|
entity |
| Predicate | chronologyPreviousTitle |
P22762
|
FINISHED |
| Object | Cardigan (song) |
E600458
|
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: Cardigan (song) | Statement: [Willow (song), chronologyPreviousTitle, Cardigan (song)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cardigan (song) Context triple: [Willow (song), chronologyPreviousTitle, Cardigan (song)]
-
A.
A Song
"A Song" is a track by Greek composer Vangelis featured on his 1979 electronic music album "Earth."
-
B.
Our Song
"Our Song" is a track by the English progressive rock band Yes, featured on their 1983 album "90125."
-
C.
White Horse
chosen
"White Horse" is a country-pop ballad by Taylor Swift that explores themes of heartbreak and disillusionment in romantic fairy-tale expectations.
-
D.
Another Song
"Another Song" is a musical track featured on the release titled "Gold Record."
-
E.
Rollstone Hill
Rollstone Hill is a prominent natural landmark overlooking the city of Fitchburg, Massachusetts, known for its rocky summit and historical significance to the local community.
- 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_69ca8436ba308190903e470776d2d893 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7c91ba1c8190b8331fb1ba58cc61 |
completed | April 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d107dd5bcc8190b3f0fdecf296fe29 |
completed | April 4, 2026, 12:45 p.m. |
Created at: March 30, 2026, 7:49 p.m.