Triple
T27337551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chicheley railway bridge |
E689995
|
entity |
| Predicate | industrySectorOfBuilder |
P165703
|
FINISHED |
| Object | steel construction |
—
|
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: steel construction | Statement: [Chicheley railway bridge, industrySectorOfBuilder, steel construction]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: industrySectorOfBuilder Context triple: [Chicheley railway bridge, industrySectorOfBuilder, steel construction]
-
A.
ownerSector
Indicates the sector or industry category to which the owner of an entity belongs.
-
B.
typeOfEnterpriseBuilt
Indicates the specific kind or category of enterprise that has been constructed or established.
-
C.
industryStart
Indicates the point in time or event at which an industry, industrial activity, or industrial era begins.
-
D.
hasIndustrialSector
Indicates that an entity is associated with, operates in, or belongs to a particular industrial sector or branch of economic activity.
-
E.
industryActivities
Indicates the types of economic or business activities in which an industry or sector is engaged.
- 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_69ef355e5b388190a8fc1eba9b4a6656 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f65b14512c8190a40e70319dcc54cd |
completed | May 2, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f659ce58408190ba9e007b4810d4d0 |
completed | May 2, 2026, 8:08 p.m. |
| PDg | Predicate description generation | batch_69f65a6babcc81908052c9907a99c882 |
completed | May 2, 2026, 8:11 p.m. |
Created at: April 27, 2026, 11:41 a.m.