Triple
T7721066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elswick |
E175010
|
entity |
| Predicate | hasTypeOfIndustryHistorical |
P3008
|
FINISHED |
| Object | heavy engineering |
—
|
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: heavy engineering | Statement: [Elswick, hasTypeOfIndustryHistorical, heavy engineering]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfIndustryHistorical Context triple: [Elswick, hasTypeOfIndustryHistorical, heavy engineering]
-
A.
hasHistoricIndustry
chosen
Indicates that an entity has been associated with a notable or historically significant industry or industrial activity in the past.
-
B.
hasHistoricalCategory
Indicates that something is associated with a particular historical classification, period, or type based on its past context or significance.
-
C.
historicalType
Indicates that one entity classifies or characterizes another in terms of its role, status, or category within a historical context.
-
D.
hasHistoricalEntity
Indicates a relationship where one entity includes, references, or is associated with another entity that existed or is defined in a past historical context.
-
E.
hasHistoricalData
Indicates that an entity possesses recorded information or records about past events, states, or values relevant to it.
- 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_69c6995d541c81909eaa646b1a8369a9 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7074eca4c8190bd51fd1b450729e8 |
completed | March 27, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69c7016a6cf88190b53bf4b958f0f302 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:05 p.m.