Triple
T16191148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cactus Flower |
E392942
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Fleur de cactus |
E392942
|
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: Fleur de cactus | Statement: [Cactus Flower, basedOn, Fleur de cactus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fleur de cactus Context triple: [Cactus Flower, basedOn, Fleur de cactus]
-
A.
Cactus Flower
chosen
Cactus Flower is a 1965 Broadway stage comedy by Abe Burrows, adapted from a French play and best known today as the basis for multiple film adaptations.
-
B.
Cactus
Cactus was the Allied codename for Henderson Field, the strategically crucial airfield on Guadalcanal during World War II.
-
C.
Cactus
"Cactus" is a song by the American alternative rock band Pixies, featured on their influential 1988 album *Surfer Rosa*.
-
D.
Desert rose
Desert rose is a striking succulent plant known for its swollen, sculptural trunk and bright tubular flowers, famously found on the isolated island of Socotra.
-
E.
Jacinto
Jacinto is the cruel caretaker and primary antagonist in Guillermo del Toro’s gothic horror film "The Devil’s Backbone."
- 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_69d87f1e49ac8190a311b54d32990576 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e222d5769c8190bbb604bfa095a1a5 |
completed | April 17, 2026, 12:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffff095504819096c36d6c5d131207 |
completed | May 10, 2026, 3:44 a.m. |
Created at: April 10, 2026, 5:02 a.m.