Triple
T24922945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HUD-1 Settlement Statement |
E618774
|
entity |
| Predicate | comparisonFunction |
P158142
|
FINISHED |
| Object | allows comparison of GFE estimates to actual charges |
—
|
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: allows comparison of GFE estimates to actual charges | Statement: [HUD-1 Settlement Statement, comparisonFunction, allows comparison of GFE estimates to actual charges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: comparisonFunction Context triple: [HUD-1 Settlement Statement, comparisonFunction, allows comparison of GFE estimates to actual charges]
-
A.
comparisonMethod
Indicates the method or criteria used to compare two or more entities or values.
-
B.
comparisonRule
Indicates a rule or criterion that defines how two or more entities are to be compared or evaluated relative to each other.
-
C.
comparisonClass
Indicates that something is being evaluated or interpreted relative to a specified reference group or standard for comparison.
-
D.
comparisonType
Indicates the specific kind of comparison being made between two or more values or entities (e.g., equality, inequality, ordering, or similarity).
-
E.
isComparisonSort
Indicates that the sorting algorithm operates by comparing pairs of elements to determine their order.
- 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_69e2fab9edd88190b86004a78a28bc20 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f464b4c9b0819085daa00c7c3b8b76 |
completed | May 1, 2026, 8:30 a.m. |
| PD | Predicate disambiguation | batch_69f45cf017a88190b4985b11159c907d |
completed | May 1, 2026, 7:57 a.m. |
| PDg | Predicate description generation | batch_69f464ae42e88190b3549fdf4e0b425e |
completed | May 1, 2026, 8:30 a.m. |
Created at: April 18, 2026, 5:29 a.m.