Triple
T10029222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rio–Niterói Bridge |
E204809
|
entity |
| Predicate | previouslyMaintainedBy |
P25617
|
FINISHED |
| Object |
CCR Ponte
CCR Ponte is a Brazilian infrastructure concession company that formerly operated and maintained the Rio–Niterói Bridge.
|
E836509
|
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: CCR Ponte | Statement: [Rio–Niterói Bridge, previouslyMaintainedBy, CCR Ponte]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CCR Ponte Context triple: [Rio–Niterói Bridge, previouslyMaintainedBy, CCR Ponte]
-
A.
Ponts
Ponts is the common short name for École des Ponts et Chaussées, one of France’s oldest and most prestigious engineering schools specializing in civil engineering, transportation, and environmental sciences.
-
B.
Ponte
Ponte is a Spanish-language surname of Iberian origin borne by various notable figures, including members of the Bolívar family.
-
C.
Z Bridge
Z Bridge is a notable bridge spanning the Mutha River in Pune, India, serving as an important local transport link.
-
D.
C Pier
C Pier is one of the passenger boarding concourses at Amsterdam Airport Schiphol, serving multiple gates for arriving and departing flights.
-
E.
Carris
Carris is the main public transport company in Lisbon, Portugal, operating the city's buses, trams, and certain historic lifts.
- 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: CCR Ponte Triple: [Rio–Niterói Bridge, previouslyMaintainedBy, CCR Ponte]
Generated description
CCR Ponte is a Brazilian infrastructure concession company that formerly operated and maintained the Rio–Niterói Bridge.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: CCR Ponte Target entity description: CCR Ponte is a Brazilian infrastructure concession company that formerly operated and maintained the Rio–Niterói Bridge.
-
A.
Ponts
Ponts is the common short name for École des Ponts et Chaussées, one of France’s oldest and most prestigious engineering schools specializing in civil engineering, transportation, and environmental sciences.
-
B.
Ponte
Ponte is a Spanish-language surname of Iberian origin borne by various notable figures, including members of the Bolívar family.
-
C.
Z Bridge
Z Bridge is a notable bridge spanning the Mutha River in Pune, India, serving as an important local transport link.
-
D.
C Pier
C Pier is one of the passenger boarding concourses at Amsterdam Airport Schiphol, serving multiple gates for arriving and departing flights.
-
E.
Carris
Carris is the main public transport company in Lisbon, Portugal, operating the city's buses, trams, and certain historic lifts.
- 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_69ca834d77188190ad645e33e8ca3200 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cdcde69bd08190a5c79ec8487dfff6 |
completed | April 2, 2026, 2:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d282351ebc8190b22bf3964823b0ee |
completed | April 5, 2026, 3:39 p.m. |
| NEDg | Description generation | batch_69d282fd10248190a1a0b4573b2065ae |
completed | April 5, 2026, 3:42 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d283d0e1748190a0c65bbaa8e8348e |
completed | April 5, 2026, 3:46 p.m. |
Created at: March 30, 2026, 8:54 p.m.