Triple
T20735096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Birmingham, Michigan |
E509679
|
entity |
| Predicate | medianHomeValue |
P97091
|
FINISHED |
| Object | above national average |
—
|
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: above national average | Statement: [Birmingham, Michigan, medianHomeValue, above national average]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: medianHomeValue Context triple: [Birmingham, Michigan, medianHomeValue, above national average]
-
A.
medianHomeValues
chosen
Indicates the typical (middle) home price or value within a given area or group of properties.
-
B.
medianHomeValueRank
Indicates the relative position of a home's value compared to other homes, typically ordered from lowest to highest within a defined group or area.
-
C.
medianHouseholdIncome
Indicates the typical (middle) value of income earned by households in a given area, such that half of households earn more and half earn less.
-
D.
houseValues
Indicates a relationship where specific houses are associated with their corresponding numerical values, such as prices or appraised worth.
-
E.
realEstatePriceLevel
Indicates the relative cost or market value level of real estate in a given context or area.
- 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_69e0b4c589c08190834fb5d86d0efa2b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c209348c819084a2f35f36378680 |
completed | April 21, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c04b31248190b9b9d91b5cb854e3 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:31 p.m.