Triple
T35154111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clybourne Park Improvement Association |
E1015070
|
entity |
| Predicate | offersToBuyBackHouseFrom |
P196717
|
FINISHED |
| Object | Younger family |
—
|
NE NERFINISHED |
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: Younger family | Statement: [Clybourne Park Improvement Association, offersToBuyBackHouseFrom, Younger family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersToBuyBackHouseFrom Context triple: [Clybourne Park Improvement Association, offersToBuyBackHouseFrom, Younger family]
-
A.
soldPropertyFor
Indicates that one entity transferred ownership of a property to another entity in exchange for a specified amount of money or value.
-
B.
offersServiceInExchangeFor
Indicates that one entity provides a service to another entity contingent upon receiving something in return (such as payment, goods, or another service).
-
C.
wantsToSell
Indicates that one entity has the intention or desire to sell another entity.
-
D.
housePosition
Indicates the spatial location or placement of a house relative to a reference point or area.
-
E.
houseStatus
Indicates the current condition or state of a house, such as whether it is occupied, vacant, under construction, or otherwise categorized.
- 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_69f76ddb3a708190b521ba2970b17178 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fe629b4fa481908467c7c41b77f0c6 |
completed | May 8, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69fe61bb260c819083f9378a3a06ca47 |
completed | May 8, 2026, 10:20 p.m. |
| PDg | Predicate description generation | batch_69fe629a8d4c8190b4aa4dee39efc0a6 |
completed | May 8, 2026, 10:24 p.m. |
Created at: May 3, 2026, 4:02 p.m.