Triple
T22206925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gratiot Avenue |
E548834
|
entity |
| Predicate | hasAlternateName |
P39
|
FINISHED |
| Object | M-3 (on certain segments) |
—
|
NE NERFINISHED |
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: M-3 (on certain segments) | Statement: [Gratiot Avenue, hasAlternateName, M-3 (on certain segments)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: M-3 (on certain segments) Context triple: [Gratiot Avenue, hasAlternateName, M-3 (on certain segments)]
-
A.
Line M3
Line M3 is a light metro route within the Charleroi Metro network in Belgium, serving suburban areas around the city.
-
B.
M-3
chosen
M-3 is a designated highway route, commonly known by its short name M-3, within a regional or national road network.
-
C.
M3 line
The M3 line is a rapid transit route within the Ankara Metro system serving parts of Turkey’s capital city.
-
D.
Line M2
Line M2 is a route of the Charleroi Metro system in Belgium, serving as part of the city's light rail rapid transit network.
-
E.
M32 line
The M32 line is a rapid transit route within the Istanbul Metro system serving commuters in Turkey’s largest city.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3f7e04819089806d81d5ac431e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12b2936a481909aa84c7983ed49ee |
completed | April 28, 2026, 9:48 p.m. |
Created at: April 16, 2026, 8:36 p.m.