Triple
T16298297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brockley |
E395708
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | New Cross |
E331211
|
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: New Cross | Statement: [Brockley, adjacentTo, New Cross]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New Cross Context triple: [Brockley, adjacentTo, New Cross]
-
A.
New Cross
chosen
New Cross is an inner-city district in southeast London known for its vibrant arts and music scene, diverse community, and proximity to Goldsmiths, University of London.
-
B.
Woodyard Crossing
Woodyard Crossing is a shopping and commercial center located in Clinton, Maryland.
-
C.
Stewart Crossing
Stewart Crossing is a small roadside community in Yukon, Canada, serving as a junction and service point for travelers along the Klondike Highway.
-
D.
Coles Crossing
Coles Crossing is a master-planned residential community located in Cypress, a suburban area northwest of Houston, Texas.
-
E.
New Cross Road
New Cross Road is a major thoroughfare in the New Cross area of southeast London, forming part of the A2 route between central London and Kent.
- 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_69d87f23bb088190a16fbb91a1957ea5 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e25e2f486c8190b73c15f59335cde2 |
completed | April 17, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a001f9d7ef48190b7acebebcb9608c3 |
completed | May 10, 2026, 6:03 a.m. |
Created at: April 10, 2026, 5:06 a.m.