Triple
T1700001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Massachusetts Correctional Institution – Shirley |
E36745
|
entity |
| Predicate | hasHousingUnits |
P31309
|
FINISHED |
| Object | medium-security housing units |
—
|
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: medium-security housing units | Statement: [Massachusetts Correctional Institution – Shirley, hasHousingUnits, medium-security housing units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHousingUnits Context triple: [Massachusetts Correctional Institution – Shirley, hasHousingUnits, medium-security housing units]
-
A.
numberOfHousingUnits
Indicates the total count of distinct housing units associated with an entity or within a specified area.
-
B.
hasNumberOfHouses
Indicates the quantity of houses associated with a given entity.
-
C.
hasHouse
Indicates that one entity possesses, owns, or is provided with a house in relation to another entity.
-
D.
hasPublicHousing
Indicates that a location or jurisdiction provides or contains government-funded residential housing available to the public.
-
E.
hasNonHumanResident
Indicates that a place or location is inhabited or occupied by one or more non-human entities.
- 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_69a886163dec8190859c514232a37a05 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf169da888190b3aa334752f1952b |
completed | March 6, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69aa61b8ce348190b46154af0b041ff0 |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69aaf16865488190a76577b36760dc7a |
completed | March 6, 2026, 3:23 p.m. |
Created at: March 4, 2026, 7:30 p.m.