Triple
T38083446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Disabled Person’s Tax Credit |
E950913
|
entity |
| Predicate | hadInteractionWith |
P3970
|
FINISHED |
| Object | income tax liability |
—
|
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: income tax liability | Statement: [Disabled Person’s Tax Credit, hadInteractionWith, income tax liability]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadInteractionWith Context triple: [Disabled Person’s Tax Credit, hadInteractionWith, income tax liability]
-
A.
hasInteraction
chosen
Indicates that there is some form of interaction or mutual action occurring between the related entities.
-
B.
hasHad
Indicates that an entity previously experienced, possessed, or was involved in something at some point in the past.
-
C.
hadCommon
Indicates that two or more entities shared the same attribute, experience, or element in common.
-
D.
hadOrgan
Indicates that an entity previously possessed or contained a specific organ as part of its body.
-
E.
hadEvent
Indicates that an entity experienced, hosted, or was associated with a specific event at some point in time.
- 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_69f76f03a3608190a73fd6df87c792a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.