Triple
T37475181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Albemarle Street literary salon |
E931258
|
entity |
| Predicate | heldAtPremisesOf |
P174643
|
FINISHED |
| Object | John Murray’s publishing house |
—
|
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: John Murray’s publishing house | Statement: [Albemarle Street literary salon, heldAtPremisesOf, John Murray’s publishing house]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heldAtPremisesOf Context triple: [Albemarle Street literary salon, heldAtPremisesOf, John Murray’s publishing house]
-
A.
heldAtLocation
Indicates that an entity is being kept or stored at a specific location.
-
B.
heldInPlaceOf
Indicates that one entity is held or conducted as a substitute or stand-in for another entity’s usual location, role, or occurrence.
-
C.
areHeldAt
chosen
Indicates that events or activities take place or occur at a specific location or venue.
-
D.
holdsAt
Indicates that a particular condition or fluent is true and persists at a specified point in time.
-
E.
heldCourtIn
Indicates that an authority or governing body formally conducted judicial or official proceedings in a particular place.
- 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_69f76ec2af148190897d101070d7f415 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8e652328819082cff21f5a1fe709 |
completed | May 6, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69fb8d0c53c08190b64291bac58cdb4c |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:17 p.m.