Triple
T11864796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Support for Mortgage Interest |
E282253
|
entity |
| Predicate | securedAgainst |
P101950
|
FINISHED |
| Object | claimant’s home |
—
|
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: claimant’s home | Statement: [Support for Mortgage Interest, securedAgainst, claimant’s home]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securedAgainst Context triple: [Support for Mortgage Interest, securedAgainst, claimant’s home]
-
A.
securityGuarantee
Indicates a commitment by one party to protect or defend another party against specified threats or risks.
-
B.
securedVariant
Indicates that one entity is a security-enhanced or more protected version of another entity.
-
C.
protectedBy
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
D.
helpedSecure
Indicates that one entity contributed to obtaining, protecting, or ensuring the safety or stability of another entity or outcome.
-
E.
securityArrangementsBy
Indicates that one entity is responsible for providing, organizing, or overseeing security arrangements for another entity or situation.
- F. None of above. chosen
Provenance (4 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a73883508190a78b5f4ba4a220df |
completed | April 10, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69d8a2589f0c8190ad82ff11acabae93 |
completed | April 10, 2026, 7:10 a.m. |
| PDg | Predicate description generation | batch_69d8a43cc0c881909fed7cd759fe90b1 |
completed | April 10, 2026, 7:18 a.m. |
Created at: April 8, 2026, 9:43 p.m.