Triple
T9859435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew station |
E239670
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Andrew Square |
E826769
|
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: Andrew Square | Statement: [Andrew station, connectsTo, Andrew Square]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Square Context triple: [Andrew station, connectsTo, Andrew Square]
-
A.
Andrew Square
chosen
Andrew Square is a neighborhood and major intersection in South Boston, Massachusetts, known as a local commercial and transit hub.
-
B.
Argyle Square
Argyle Square is a retail shopping center located in Wilsonville, Oregon, featuring a variety of stores and services for local residents and visitors.
-
C.
Forster Square
Forster Square is a public square and transport hub in central Bradford, West Yorkshire, known for its adjacent railway station and nearby shopping and commercial developments.
-
D.
South Square
South Square is a major plaza and passenger hub area located at Chongqing North Railway Station in Chongqing, China.
-
E.
Stockel Square
Stockel Square is a shopping and commercial center located in the Woluwe-Saint-Pierre municipality of Brussels, Belgium.
- 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_69ca84e6493081909cf58c8d42ea856b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb39b06b48190ab53ff00ff0513ca |
completed | April 2, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1ead91ee88190bd4cb28ab16bf703 |
completed | April 5, 2026, 4:53 a.m. |
Created at: March 30, 2026, 8:35 p.m.