Triple
T15480178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pedder Street |
E376893
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | The Landmark |
E1004387
|
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 Landmark | Statement: [Pedder Street, near, The Landmark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Landmark Context triple: [Pedder Street, near, The Landmark]
-
A.
The Landmark
chosen
The Landmark is a prominent luxury commercial and shopping complex in Central, Hong Kong, known for its high-end retail stores, offices, and hotels.
-
B.
The Chambers
The Chambers is the English title of the work originally known as "The Rooms."
-
C.
The House
The House is a film edited by Alan Baumgarten, known for his work on acclaimed movies such as The Trial of the Chicago 7 and American Hustle.
-
D.
The House
"The House" is a poem from the interactive fiction work *Live or Die*, likely exploring themes of choice, mortality, and psychological tension within a domestic setting.
-
E.
The House
The House is a pioneering high-rise residential building on Cornell Tech’s Roosevelt Island campus, known for its ultra-energy-efficient, sustainable design.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f8a77a081909f12f13660452f4a |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2d0d6ef0819091623de2888a7101 |
completed | May 9, 2026, 12:48 p.m. |
Created at: April 10, 2026, 3:34 a.m.