Triple
T37504919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Downing Street memo |
E932065
|
entity |
| Predicate | meetingParticipantsIncluded |
P33356
|
FINISHED |
| Object | Tony Blair |
—
|
NE NERFINISHED |
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: Tony Blair | Statement: [Downing Street memo, meetingParticipantsIncluded, Tony Blair]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: meetingParticipantsIncluded Context triple: [Downing Street memo, meetingParticipantsIncluded, Tony Blair]
-
A.
firstMeetingParticipants
Indicates that the related entities are participants involved in a first-time meeting or initial encounter.
-
B.
invitedParticipant
Indicates that an entity has been invited to take part in an event, activity, or interaction.
-
C.
eventParticipant
chosen
Indicates that an entity takes part in, is involved in, or participates in a particular event.
-
D.
hasParticipants
Indicates that an event, activity, or situation involves one or more entities as participants in it.
-
E.
participationIncludes
Indicates that a broader participation instance encompasses or contains a more specific participation instance as part of it.
- 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_69f76ec5268481909ea01c73aeeefd42 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:17 p.m.