Triple
T12764955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Anne's MCR |
E305097
|
entity |
| Predicate | isCommonRoomFor |
P43700
|
FINISHED |
| Object | St Anne's College graduate members |
—
|
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: St Anne's College graduate members | Statement: [St Anne's MCR, isCommonRoomFor, St Anne's College graduate members]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCommonRoomFor Context triple: [St Anne's MCR, isCommonRoomFor, St Anne's College graduate members]
-
A.
hasCommonRoomEntranceType
Indicates that two or more rooms share the same type or style of entrance.
-
B.
hasMiddleCommonRoom
chosen
Indicates that two entities share access to or use of the same middle common room space.
-
C.
hasRoom
Indicates that an entity possesses, contains, or is associated with a specific room.
-
D.
houseCommonRoom
Indicates that a house or dwelling includes or is associated with a shared common room space used collectively by its occupants.
-
E.
hasCommonSpace
Indicates that two or more entities share access to the same physical or virtual area intended for joint or overlapping use.
- 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_69d7bdf1fcd081909ffb0e0d6fa3a07d |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96df1ef148190af525532fcb0933b |
completed | April 10, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69d96409739881909174ba005a986cb5 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:28 p.m.