Triple
T14596340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamar Valley |
E342577
|
entity |
| Predicate | hasBridge |
P386
|
FINISHED |
| Object | Tamar Bridge |
E450967
|
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: Tamar Bridge | Statement: [Tamar Valley, hasBridge, Tamar Bridge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tamar Bridge Context triple: [Tamar Valley, hasBridge, Tamar Bridge]
-
A.
Tamar Bridge
chosen
Tamar Bridge is a major suspension bridge in southwest England that carries road traffic between Plymouth in Devon and Saltash in Cornwall across the River Tamar.
-
B.
Teg Bridge
Teg Bridge is a major road bridge in Umeå, Sweden, that spans the Ume River and connects the city center with the district of Teg.
-
C.
Pye Bridge
Pye Bridge is a small village and former industrial settlement in Derbyshire, England, historically associated with coal mining and railways.
-
D.
Benson Bridge
Benson Bridge is a historic pedestrian footbridge that spans the lower falls at Oregon’s Multnomah Falls, offering visitors a close-up view of the cascading water.
-
E.
Morrison Bridge
The Morrison Bridge is a bascule bridge spanning the Willamette River in downtown Portland, Oregon, carrying both vehicle and pedestrian traffic.
- 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb43581348190b5362251c3a89654 |
completed | April 14, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00679214208190a9ee4cce882f59cb |
completed | May 10, 2026, 11:10 a.m. |
Created at: April 10, 2026, 1:25 a.m.