Triple
T37203019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lumo (Class 803 variant) |
E922091
|
entity |
| Predicate | relatedBiModeClass |
P70655
|
FINISHED |
| Object | British Rail Class 802 |
E269459
|
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: British Rail Class 802 | Statement: [Lumo (Class 803 variant), relatedBiModeClass, British Rail Class 802]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedBiModeClass Context triple: [Lumo (Class 803 variant), relatedBiModeClass, British Rail Class 802]
-
A.
relatedClassification
Indicates a relationship where one classification is associated with, linked to, or otherwise contextually connected to another classification.
-
B.
bidirectionalClass
chosen
Indicates that a class participates in a bidirectional relationship, where each related class maintains a reference to the other.
-
C.
relatedInterface
Indicates that one interface is associated or connected to another interface in a relevant or dependent way.
-
D.
relatedType
Indicates that one entity is connected to another through a specified type or category of relationship.
-
E.
relatedPattern
Indicates that one entity is associated with or connected to another through a shared or corresponding pattern.
- F. None of above.
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_69f76ea4849481909b4a3073efb0114c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a4043b6ef788190bb286997844c07be |
completed | June 27, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.