Triple
T19990975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line 3 |
E494061
|
entity |
| Predicate | hasSystem |
P730
|
FINISHED |
| Object |
STC Metro
STC Metro is the rapid transit system serving Riyadh, Saudi Arabia, as part of the city’s integrated public transportation network.
|
E1407310
|
NE FINISHED |
How this triple was built (4 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: STC Metro | Statement: [Line 3, hasSystem, STC Metro]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: STC Metro Context triple: [Line 3, hasSystem, STC Metro]
-
A.
STC Metro
STC Metro is the rapid transit system serving Mexico City and some surrounding areas, known as one of the largest and busiest metro networks in Latin America.
-
B.
STL Metro
STL Metro is a public transit system serving the St. Louis metropolitan area with buses and light rail services.
-
C.
Sun Metro
Sun Metro is the public transportation agency serving the city of El Paso, Texas, operating local bus routes and related transit services.
-
D.
CapMetro
CapMetro is the public transportation authority serving the Austin, Texas metropolitan area, operating bus, rail, and paratransit services.
-
E.
Carris Metropolitana
Carris Metropolitana is a public transport company that operates bus services across the Lisbon metropolitan area in Portugal.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: STC Metro Triple: [Line 3, hasSystem, STC Metro]
Generated description
STC Metro is the rapid transit system serving Riyadh, Saudi Arabia, as part of the city’s integrated public transportation network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: STC Metro Target entity description: STC Metro is the rapid transit system serving Riyadh, Saudi Arabia, as part of the city’s integrated public transportation network.
-
A.
STC Metro
STC Metro is the rapid transit system serving Mexico City and some surrounding areas, known as one of the largest and busiest metro networks in Latin America.
-
B.
STL Metro
STL Metro is a public transit system serving the St. Louis metropolitan area with buses and light rail services.
-
C.
Sun Metro
Sun Metro is the public transportation agency serving the city of El Paso, Texas, operating local bus routes and related transit services.
-
D.
CapMetro
CapMetro is the public transportation authority serving the Austin, Texas metropolitan area, operating bus, rail, and paratransit services.
-
E.
Carris Metropolitana
Carris Metropolitana is a public transport company that operates bus services across the Lisbon metropolitan area in Portugal.
- F. None of above. chosen
Provenance (5 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fe00b908190bda6b9a3a3281ec0 |
completed | April 20, 2026, 5:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a080e1c30c48190973e2735ecef8354 |
completed | May 16, 2026, 6:26 a.m. |
| NEDg | Description generation | batch_6a08100875fc8190a60561870c8b6e32 |
completed | May 16, 2026, 6:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a081080c9908190a6029049afe65004 |
completed | May 16, 2026, 6:36 a.m. |
Created at: April 11, 2026, 3:31 p.m.