Triple
T12766721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingston SE |
E305142
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Big Lobster |
E1001940
|
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: Big Lobster | Statement: [Kingston SE, hasLandmark, Big Lobster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Big Lobster Context triple: [Kingston SE, hasLandmark, Big Lobster]
-
A.
the Big Lobster
chosen
The Big Lobster is a giant roadside crustacean sculpture and popular tourist attraction located in Kingston SE, South Australia.
-
B.
Lobster Telephone
Lobster Telephone is a surrealist sculpture by Salvador Dalí that combines a lobster and a telephone to create an absurd, dreamlike everyday object.
-
C.
Big Tuna
Big Tuna is the nickname of Tony Accardo, a powerful and long-serving boss of the Chicago Outfit organized crime syndicate.
-
D.
The Big Meal
The Big Meal is a stage play by Dan LeFranc that traces multiple generations of a family through a series of interconnected restaurant conversations.
-
E.
The Big Cheese
"The Big Cheese" is a track by the experimental rock band Uncommon Ritual, likely showcasing their distinctive, genre-blending musical style.
- 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_69d7bdf1fcd081909ffb0e0d6fa3a07d |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96df1ef148190af525532fcb0933b |
completed | April 10, 2026, 9:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69b90ae688190b22e3a68d27b54c5 |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 9, 2026, 5:28 p.m.