Triple
T12409461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Argyll Street |
E296476
|
entity |
| Predicate | servedBy |
P82
|
FINISHED |
| Object | Central line |
E59706
|
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: Central line | Statement: [Argyll Street, servedBy, Central line]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Central line Context triple: [Argyll Street, servedBy, Central line]
-
A.
Central line
chosen
The Central line is one of the principal lines of the London Underground, running east–west across Greater London and serving many key central and suburban areas.
-
B.
Central Line
The Central Line is one of the major suburban railway corridors in Mumbai, India, connecting the city with its eastern and northeastern suburbs and satellite towns.
-
C.
Central Line
The Central Line is a major railway in Tanzania that runs from Dar es Salaam inland, serving as a key transport corridor across the country.
-
D.
PICC
PICC is a major convention and exhibition center in Metro Manila, Philippines, known for hosting international conferences, cultural events, and government functions.
-
E.
PICC
PICC is a major convention and exhibition venue located in Putrajaya, Malaysia, known for hosting international conferences and events.
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d4b86c88190afba0de15b34eee9 |
completed | April 10, 2026, 7:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671852f588190924ded1c0a360b47 |
completed | May 2, 2026, 9:49 p.m. |
Created at: April 8, 2026, 9:55 p.m.