Triple
T6723062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NHS Tax Credit Exemption Certificate |
E153442
|
entity |
| Predicate | holderMust |
P34434
|
FINISHED |
| Object | be named on a qualifying tax credit award |
—
|
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: be named on a qualifying tax credit award | Statement: [NHS Tax Credit Exemption Certificate, holderMust, be named on a qualifying tax credit award]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holderMust Context triple: [NHS Tax Credit Exemption Certificate, holderMust, be named on a qualifying tax credit award]
-
A.
holderMustBe
chosen
Indicates that a specified entity is required to be the holder or possessor of another entity or resource.
-
B.
holderIs
Indicates that one entity serves as the holder, possessor, or container of another entity.
-
C.
holderMayBe
Indicates that a particular entity is allowed or permitted to serve as the holder or possessor of another entity.
-
D.
holdsFor
Indicates that a particular relationship or condition remains true over a specified interval or duration of time.
-
E.
holdsUnder
Indicates that one entity maintains possession, control, or validity of another entity subject to certain conditions, constraints, or a specific context.
- 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_69c6880afb988190ad88011b48ecfcba |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d13b296c8190bf54009063032c6d |
completed | March 27, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69c6d08c5d348190a29dee668c398e70 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:08 p.m.