Triple
T4622131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auckland Harbour Bridge |
E101009
|
entity |
| Predicate | widenedBy |
P9926
|
FINISHED |
| Object | clip-on box girder extensions |
—
|
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: clip-on box girder extensions | Statement: [Auckland Harbour Bridge, widenedBy, clip-on box girder extensions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: widenedBy Context triple: [Auckland Harbour Bridge, widenedBy, clip-on box girder extensions]
-
A.
expandedBy
Indicates that one entity increases, elaborates, or builds upon the scope, detail, or extent of another entity.
-
B.
extendedBy
chosen
Indicates that one entity builds upon, enlarges, or adds to the scope, functionality, or duration of another entity.
-
C.
extendedFrom
Indicates that one entity is derived by adding to or building upon the scope, content, or structure of another entity.
-
D.
expandedAcross
Indicates that something has grown or extended so that it now spans or covers multiple areas, regions, or segments.
-
E.
extendedIn
Indicates that one entity continues, prolongs, or expands the scope, duration, or range of another entity.
- F. None of above.
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_69bd43d0497c8190ac23c65c5804846a |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a0374308190aeaffc9d866a3742 |
completed | March 20, 2026, 2:30 p.m. |
| PD | Predicate disambiguation | batch_69bd5231db7c8190b38d4fdbad8bf842 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:12 p.m.