Triple
T13742210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strangeways Prison, Manchester |
E330111
|
entity |
| Predicate | hasGallows |
P110802
|
FINISHED |
| Object | former execution chamber |
—
|
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: former execution chamber | Statement: [Strangeways Prison, Manchester, hasGallows, former execution chamber]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGallows Context triple: [Strangeways Prison, Manchester, hasGallows, former execution chamber]
-
A.
hungFrom
Indicates that one entity is suspended and supported by another entity from above.
-
B.
hasMannerOfDeath
Indicates the specific way or circumstances in which an entity died, such as natural causes, accident, homicide, or suicide.
-
C.
hasGraves
Indicates that an entity possesses, contains, or is associated with one or more graves.
-
D.
hasNotablePersonExecuted
Indicates that a notable or prominent person has been subjected to execution (e.g., capital punishment) in relation to the referenced entity.
-
E.
executioner
Indicates that one entity performs or is responsible for carrying out an execution on another entity.
- 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_69d80772315881908f980cae40d91664 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69de020855ec8190a60fa1cb761f2e68 |
completed | April 14, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69dbbe950b148190ba0df8a749269ec6 |
completed | April 12, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69dbc59db0148190bcaf9646403ca64f |
completed | April 12, 2026, 4:17 p.m. |
Created at: April 9, 2026, 9:55 p.m.