Triple
T38017650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Housing Benefit (for most new working-age claimants) |
E948539
|
entity |
| Predicate | paymentDestination |
P152030
|
FINISHED |
| Object | tenant |
—
|
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: tenant | Statement: [Housing Benefit (for most new working-age claimants), paymentDestination, tenant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paymentDestination Context triple: [Housing Benefit (for most new working-age claimants), paymentDestination, tenant]
-
A.
paymentRecipient
Indicates the entity that receives a payment from another party in a transaction.
-
B.
fundingDestination
chosen
Indicates the target entity or purpose to which financial resources are allocated or directed.
-
C.
paymentSystem
Indicates a relationship where one entity functions as a mechanism or platform through which another entity makes or processes payments.
-
D.
paymentSource
Indicates the origin or method from which a payment is provided or funded in a transaction.
-
E.
paymentMethod
Indicates the means or instrument through which a payment is made in a transaction.
- 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_69f76efc10448190aff5fb566b98f952 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.