Triple
T13878618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Long Jetty |
E333647
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | The Entrance |
E66641
|
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: The Entrance | Statement: [Long Jetty, adjacentTo, The Entrance]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Entrance Context triple: [Long Jetty, adjacentTo, The Entrance]
-
A.
The Entrance
chosen
The Entrance is a popular coastal town on the New South Wales Central Coast known for its beaches, waterfront promenade, and family-friendly attractions.
-
B.
The Door
"The Door" is a pivotal and emotionally charged episode of Game of Thrones renowned for revealing the origin of Hodor's name and fate.
-
C.
The Gate
The Gate is a 1987 supernatural horror film about children who accidentally unleash demonic forces from a mysterious hole in their backyard.
-
D.
The Gate
The Gate is a 1910 novel by Japanese author Natsume Sōseki that quietly explores themes of guilt, marriage, and spiritual searching in Meiji-era Japan.
-
E.
The Guest Book
The Guest Book is an American comedy television series that follows the quirky misadventures of various guests staying at a small-town vacation rental.
- 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_69d81c5ced9c8190b0e9bcc6effe5959 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0be71d388190909290cad2c6daf5 |
completed | April 14, 2026, 9:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c7100b308190bdd5feaa116ee5fe |
completed | May 3, 2026, 10:07 p.m. |
Created at: April 9, 2026, 10:15 p.m.