Triple
T19304826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Gorge Bridge |
E482796
|
entity |
| Predicate | wasWorldsHighestBridgeFrom |
P135197
|
FINISHED |
| Object | 1929 |
—
|
LITERAL 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: 1929 | Statement: [Royal Gorge Bridge, wasWorldsHighestBridgeFrom, 1929]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasWorldsHighestBridgeFrom Context triple: [Royal Gorge Bridge, wasWorldsHighestBridgeFrom, 1929]
-
A.
wasWorldsLongestSuspensionBridgeSpan
Indicates that something held the record for having the longest main span of any suspension bridge in the world at a given time.
-
B.
isOldestSurvivingBridgeAcross
Indicates that a bridge is the most ancient still-existing bridge that spans a specified waterway, road, or gap.
-
C.
wasLongestBridgeInSoutheastAsiaUntil
Indicates that a bridge held the status of being the longest in Southeast Asia up to a specified point in time.
-
D.
wasWorldsLongestCableStayedBridgeAtOpening
Indicates that the bridge held the record as the world’s longest cable-stayed bridge at the time it was opened.
-
E.
wasWorldsLongestConcreteArchSpan
Indicates that something held the record for being the world's longest concrete arch span.
- F. None of above. chosen
Provenance (4 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e604c744908190975c71a28acc96cc |
completed | April 20, 2026, 10:49 a.m. |
| PD | Predicate disambiguation | batch_69e4dd0bc7508190a6f9d56bd4c3404f |
completed | April 19, 2026, 1:47 p.m. |
| PDg | Predicate description generation | batch_69e4ddcf50108190a09d0f1291c17374 |
completed | April 19, 2026, 1:51 p.m. |
Created at: April 10, 2026, 1:31 p.m.