Triple
T15632829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tommy Carcetti |
E375860
|
entity |
| Predicate | campaignsForOffice |
P75922
|
FINISHED |
| Object | Mayor of Baltimore |
—
|
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: Mayor of Baltimore | Statement: [Tommy Carcetti, campaignsForOffice, Mayor of Baltimore]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campaignsForOffice Context triple: [Tommy Carcetti, campaignsForOffice, Mayor of Baltimore]
-
A.
campaignForOffice
chosen
Indicates that an individual is actively seeking election to a public office or position through an organized political campaign.
-
B.
campaigns
Indicates that an entity actively conducts or participates in an organized effort or series of actions aimed at achieving a specific goal, often in political, marketing, or advocacy contexts.
-
C.
nominatedForOffice
Indicates that an entity has been formally put forward as a candidate to hold a particular office or position.
-
D.
electionForOffice
Indicates that an election event is held to select or fill a specific office or position.
-
E.
campaignFinanceContext
Indicates the relationship in which an action, event, or statement occurs within the specific circumstances, rules, or issues related to campaign financing.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04eb7338881909f3c430bb73f91d1 |
completed | April 16, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_69deda868d4481908f4bce1c64d2902a |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:14 a.m.