Triple
T19545452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brooke Shields |
E489034
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Blue Lagoon |
—
|
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: The Blue Lagoon | Statement: [Brooke Shields, notableWork, The Blue Lagoon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Blue Lagoon Context triple: [Brooke Shields, notableWork, The Blue Lagoon]
-
A.
The Blue Lagoon
chosen
The Blue Lagoon is a 1980 romantic survival film about two young castaways growing up together on a remote tropical island.
-
B.
Blue Lagoon
Blue Lagoon is a famous crystal-clear turquoise bay on the Maltese island of Comino, popular for swimming, snorkeling, and boat excursions.
-
C.
Blue Lagoon
Blue Lagoon is a German Eurodance duo known for their early-2000s dance-pop covers of classic hits.
-
D.
Blue Lagoon
Blue Lagoon is a famous turquoise-colored mineral spring and swimming spot on Jamaica’s eastern coast, popular for its scenic beauty and calm, deep waters.
-
E.
Blue Lagoon
Blue Lagoon is a famous geothermal spa in Iceland known for its milky-blue mineral-rich waters and surrounding volcanic landscape.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63876bacc8190b17e2087de679785 |
completed | April 20, 2026, 2:30 p.m. |
Created at: April 10, 2026, 1:41 p.m.