Triple
T11434268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morton’s Tower |
E270963
|
entity |
| Predicate | residenceAccessed |
P99286
|
FINISHED |
| Object | Archbishop of Canterbury’s official London residence |
—
|
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: Archbishop of Canterbury’s official London residence | Statement: [Morton’s Tower, residenceAccessed, Archbishop of Canterbury’s official London residence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: residenceAccessed Context triple: [Morton’s Tower, residenceAccessed, Archbishop of Canterbury’s official London residence]
-
A.
houseVisited
Indicates that a particular house has been visited by a specified entity or at a specified time.
-
B.
residence
Indicates that one entity lives at, is based in, or habitually occupies the location represented by the other entity.
-
C.
hasResidenceFeature
Indicates that a residence possesses or is characterized by a specific feature or attribute.
-
D.
residenceUsedFor
Indicates that a particular residence is used for a specific purpose, function, or activity.
-
E.
residenceDuringEvent
Indicates that an entity resides or is located at a particular place for the duration of a specified event.
- 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d806c485f481909dd3d9b0993f3faf |
completed | April 9, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69d7e71436f88190ac7e45a04ea5c987 |
completed | April 9, 2026, 5:51 p.m. |
| PDg | Predicate description generation | batch_69d80010712c819089ea2e31e664abe1 |
completed | April 9, 2026, 7:37 p.m. |
Created at: April 8, 2026, 9:35 p.m.