Triple
T2306337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unit 3 residence halls (UC Berkeley) |
E51847
|
entity |
| Predicate | primarilyHouses |
P1643
|
FINISHED |
| Object | first-year students |
—
|
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: first-year students | Statement: [Unit 3 residence halls (UC Berkeley), primarilyHouses, first-year students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primarilyHouses Context triple: [Unit 3 residence halls (UC Berkeley), primarilyHouses, first-year students]
-
A.
houses
chosen
Indicates that one entity serves as a dwelling or shelter for another entity.
-
B.
house1
Indicates that something is identified or classified as a house or dwelling.
-
C.
house2
Indicates a relationship where one entity is a secondary, related, or alternative house associated with another entity.
-
D.
residence
Indicates that one entity lives at, is based in, or habitually occupies the location represented by the other entity.
-
E.
associatedHouse
Indicates a relationship where one entity is linked or connected to a particular house, typically as its related or corresponding house.
- 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_69a88b0bb30c81908ded03b006d29387 |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abce1f4f0c8190a714e4dcb8449f7e |
completed | March 7, 2026, 7:05 a.m. |
| PD | Predicate disambiguation | batch_69abc58ce2a081908ce2f0cadd92e9f8 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:49 p.m.