Triple
T19644775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Trees They Do Grow High |
E471644
|
entity |
| Predicate | hasVariantTitle |
P455
|
FINISHED |
| Object | Lady Mary Ann |
—
|
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: Lady Mary Ann | Statement: [The Trees They Do Grow High, hasVariantTitle, Lady Mary Ann]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lady Mary Ann Context triple: [The Trees They Do Grow High, hasVariantTitle, Lady Mary Ann]
-
A.
Grand Bonny
Grand Bonny is the traditional name for Bonny, a historic coastal town and former trading hub in Rivers State, Nigeria.
-
B.
Sloop John B
"Sloop John B" is a popular folk song famously adapted and recorded by the Beach Boys on their landmark 1966 album "Pet Sounds."
-
C.
Gracy
Gracy is a given name, typically used as a feminine variant of the name Gracie or Grace.
-
D.
Mary Ann
chosen
Mary Ann is a feminine given name, traditionally a compound of "Mary" and "Ann," used in various English-speaking cultures.
-
E.
Mary Ann
Mary Ann is a fictional character known as the ex-wife of Ray Ferrier in the 2005 film adaptation of "War of the Worlds."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e6412452d481908b6946cad3c411d5 |
completed | April 20, 2026, 3:07 p.m. |
Created at: April 10, 2026, 1:44 p.m.