Triple
T15926318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Girl Crush |
E386213
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Liz Rose |
E812542
|
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: Liz Rose | Statement: [Girl Crush, writer, Liz Rose]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liz Rose Context triple: [Girl Crush, writer, Liz Rose]
-
A.
Liz Rose
chosen
Liz Rose is an American country music songwriter best known for her frequent collaborations with Taylor Swift on several of Swift’s early hit songs.
-
B.
Liza Elliott
Liza Elliott is the conflicted, high-powered fashion magazine editor whose psychoanalytic journey drives the plot of the musical "Lady in the Dark."
-
C.
Liza Owen
Liza Owen is a British-Cambodian singer-songwriter known for her pop and R&B-influenced writing and collaborations with major contemporary artists.
-
D.
Liza Todd
Liza Todd is an American sculptor and the daughter of actress Elizabeth Taylor and producer Mike Todd.
-
E.
Rosie Richardson
Rosie Richardson is the protagonist of Helen Fielding’s novel "Cause Celeb," a young woman who leaves her London media job to work at a refugee camp in Africa, navigating both personal and political challenges.
- 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_69d86da750008190987eb26be3f6c118 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156866de48190a744e8dcaa0c66f1 |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe46b06688190a02fee3700efd709 |
completed | May 10, 2026, 1:50 a.m. |
Created at: April 10, 2026, 4:52 a.m.