Triple
T34621180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colas Rail |
E889005
|
entity |
| Predicate | operatesForClient |
P35093
|
FINISHED |
| Object | Network Rail |
—
|
NE NERFINISHED |
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: Network Rail | Statement: [Colas Rail, operatesForClient, Network Rail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesForClient Context triple: [Colas Rail, operatesForClient, Network Rail]
-
A.
operatedForClientType
Indicates that an operation or service is performed specifically on behalf of, or tailored to, a particular type or category of client.
-
B.
operatesOver
Indicates that one entity performs actions or exerts functional control across, upon, or throughout another entity or domain.
-
C.
clientOf
chosen
Indicates that one entity receives services or conducts business from another entity in a client–provider relationship.
-
D.
operatesForTenant
Indicates that an entity performs operations or provides services on behalf of, or under the authority of, a specific tenant.
-
E.
operatedFor
Indicates that one entity performed operations or provided services on behalf of, or in support of, another entity for a certain period or purpose.
- 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_69f349d584e08190b40b9f6281ad50c4 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00c8e617548190bba4cdfbb6f512e0 |
completed | May 10, 2026, 6:05 p.m. |
| PD | Predicate disambiguation | batch_6a00c7e816b88190bd40f5ea2a768c8b |
completed | May 10, 2026, 6:01 p.m. |
Created at: May 1, 2026, 2:04 a.m.