Triple
T15572516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kessock Bridge |
E374280
|
entity |
| Predicate | designer |
P184
|
FINISHED |
| Object |
William Brown
William Brown is a civil engineer best known for designing Scotland’s Kessock Bridge, a prominent cable-stayed road bridge near Inverness.
|
E1165241
|
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: William Brown | Statement: [Kessock Bridge, designer, William Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Brown Context triple: [Kessock Bridge, designer, William Brown]
-
A.
William Brown
William Brown was a civil engineer known for his role in the design and construction of the Severn Bridge in the United Kingdom.
-
B.
William Brown
William Brown was an American Revolutionary War soldier recognized as the first recipient of the Badge of Military Merit, a precursor to the modern Purple Heart.
-
C.
William Brown
William Brown is an author known for contributing to the book "Around the Way Girl."
-
D.
William Brown
William Brown was an engineer best known for his role in designing Istanbul’s iconic Bosporus Bridge, one of the world’s major suspension bridges connecting Europe and Asia.
-
E.
William Brown
William Brown was an Irish-born admiral who became a national hero in Argentina as the founder and first commander of its navy.
- 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: William Brown Triple: [Kessock Bridge, designer, William Brown]
Generated description
William Brown is a civil engineer best known for designing Scotland’s Kessock Bridge, a prominent cable-stayed road bridge near Inverness.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: William Brown Target entity description: William Brown is a civil engineer best known for designing Scotland’s Kessock Bridge, a prominent cable-stayed road bridge near Inverness.
-
A.
William Brown
William Brown was an engineer best known for his role in designing Istanbul’s iconic Bosporus Bridge, one of the world’s major suspension bridges connecting Europe and Asia.
-
B.
William Brown
William Brown was a civil engineer known for his role in the design and construction of the Severn Bridge in the United Kingdom.
-
C.
William Brown
William Brown was an American Revolutionary War soldier recognized as the first recipient of the Badge of Military Merit, a precursor to the modern Purple Heart.
-
D.
William Brown
William Brown is an author known for contributing to the book "Around the Way Girl."
-
E.
William Brown
William Brown was an Irish-born admiral who became a national hero in Argentina as the founder and first commander of its navy.
- 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e2025888190a2b6240296bba13e |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c4767e48190a180062688cdc245 |
completed | May 9, 2026, 3:01 p.m. |
| NEDg | Description generation | batch_69ff507a84c081909ab592497be644fb |
completed | May 9, 2026, 3:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff50f653f48190ae5bd6fcb5665041 |
completed | May 9, 2026, 3:21 p.m. |
Created at: April 10, 2026, 4:10 a.m.