Triple
T1400000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Board of Health of Toronto |
E30756
|
entity |
| Predicate | hasCommitteeRole |
P18442
|
FINISHED |
| Object | sets strategic direction for Toronto Public Health |
—
|
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: sets strategic direction for Toronto Public Health | Statement: [Board of Health of Toronto, hasCommitteeRole, sets strategic direction for Toronto Public Health]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCommitteeRole Context triple: [Board of Health of Toronto, hasCommitteeRole, sets strategic direction for Toronto Public Health]
-
A.
hasCommittee
Indicates that an entity is associated with or overseen by a specific committee.
-
B.
hasCommitteeFunction
chosen
Indicates that a committee is assigned or performs a specific function, role, or responsibility.
-
C.
hasCommitteeType
Indicates that an entity is associated with a committee of a specified type or classification.
-
D.
hasNotableMemberCommittee
Indicates that a committee includes at least one member who is notable or distinguished in some recognized way.
-
E.
hasPoliticalRole
Indicates that an entity holds, has held, or is assigned a specific political office, function, or position in relation to another entity or context.
- 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_69a498fd4e408190bd73eca30ea9754c |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c39c4c148190997150996ca26a99 |
completed | March 1, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69a4bf017f8081908572121560ec621f |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.