Triple
T26635711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Columbia Point Housing Project |
E668629
|
entity |
| Predicate | occupancyRate |
P138287
|
FINISHED |
| Object | very low by late 1970s |
—
|
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: very low by late 1970s | Statement: [Columbia Point Housing Project, occupancyRate, very low by late 1970s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occupancyRate Context triple: [Columbia Point Housing Project, occupancyRate, very low by late 1970s]
-
A.
reservationPercentage
chosen
Indicates the proportion of a resource, capacity, or allocation that is reserved relative to its total available amount.
-
B.
approximateOccupation
Indicates that one entity is inferred or estimated to be the occupation or job role of another entity, rather than being known with certainty.
-
C.
hostOccupation
Indicates that one entity serves as the primary job, profession, or role held by another entity.
-
D.
hasOccupancyStatus
Indicates the current usage or availability state of something, such as whether it is occupied, vacant, or otherwise in use.
-
E.
occupancyRequirement
Indicates that a condition specifies how many or which entities must be present in or using a particular space or resource.
- 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_69ee9d0024b8819090a7c8cf669a3b6c |
completed | April 26, 2026, 11:17 p.m. |
| NER | Named-entity recognition | batch_69f650c70d7c819093d9a0f005f7c8d5 |
completed | May 2, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69f64cab1f648190a2a9460690d18a37 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 2:27 a.m.