Triple
T11259587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Child Tax Credit |
E266525
|
entity |
| Predicate | canBeRefundable |
P98154
|
FINISHED |
| Object | yes, up to certain limits depending on year |
—
|
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: yes, up to certain limits depending on year | Statement: [Child Tax Credit, canBeRefundable, yes, up to certain limits depending on year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeRefundable Context triple: [Child Tax Credit, canBeRefundable, yes, up to certain limits depending on year]
-
A.
canBeRebatedTo
chosen
Indicates that a cost, fee, or amount is eligible to be refunded or credited back to a specified party.
-
B.
canBeRevoked
Indicates that a previously granted status, permission, or agreement is subject to being withdrawn or canceled.
-
C.
canBeRecycled
Indicates that an item or material is suitable for processing so it can be reused or converted into new products instead of being discarded as waste.
-
D.
canRejectBills
Indicates the authority or power an entity has to refuse approval of proposed bills or legislative measures.
-
E.
canBeAwarded
Indicates that an entity is eligible to receive or be granted a particular award, prize, or honor.
- 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_69d6aac7953c8190b82caf9d7640fdf9 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e936cb048190b4d6fb2851ef8932 |
completed | April 9, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69d7879bc56c8190b2e8d2193f29de05 |
completed | April 9, 2026, 11:03 a.m. |
Created at: April 8, 2026, 9:31 p.m.