Triple
T22152653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Basil Hallward |
E547450
|
entity |
| Predicate | meetsDorianAt |
P1220
|
FINISHED |
| Object | Lady Brandon’s party |
—
|
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: Lady Brandon’s party | Statement: [Basil Hallward, meetsDorianAt, Lady Brandon’s party]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meetsDorianAt Context triple: [Basil Hallward, meetsDorianAt, Lady Brandon’s party]
-
A.
rendezvousWith
Indicates that two or more entities meet or come together at an agreed place and time, often for a specific purpose.
-
B.
meetsRodolfoBecause
Indicates that one entity meets Rodolfo as a consequence of, or for the reason specified by, another related circumstance or factor.
-
C.
firstMeetingPlace
Indicates the location where two or more entities met each other for the very first time.
-
D.
meets
chosen
Indicates that two or more entities come together at the same place and time, typically for interaction or a shared purpose.
-
E.
meetsAs
Indicates that two entities encounter or come together at the same place and time, typically in a planned or recognized interaction.
- 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_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f5a740819093628386732b91a6 |
completed | April 28, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69e71b384e008190b723c9a0f1089d66 |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:33 p.m.