Triple
T37393849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2016 Ellicott City flood |
E928792
|
entity |
| Predicate | governmentResponseBy |
P204191
|
FINISHED |
| Object | Howard County government |
E2117677
|
NE 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: Howard County government | Statement: [2016 Ellicott City flood, governmentResponseBy, Howard County government]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governmentResponseBy Context triple: [2016 Ellicott City flood, governmentResponseBy, Howard County government]
-
A.
governmentRespondent
Indicates that the entity functions as a government body or authority serving as the respondent in a legal, administrative, or formal proceeding.
-
B.
governmentAction
Indicates actions, decisions, or interventions carried out by a government or its agencies in relation to other entities.
-
C.
governmentOutcome
Indicates the result, consequence, or effect produced by a government’s decisions, actions, or policies.
-
D.
government2
Indicates a relationship where an entity serves as or functions as the governing authority or administrative body over another entity.
-
E.
government1
Indicates that one entity functions as the governing authority or administration over another entity.
- F. None of above. chosen
Provenance (5 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_69f76ebb10c481909b54b9dba263e29f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a034540e37c819087a5c75c559323d8 |
completed | May 12, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40770346288190ad8ccbbb9f87efd1 |
completed | June 28, 2026, 1:21 a.m. |
| PD | Predicate disambiguation | batch_6a0344e26fec8190867227f9692e92df |
completed | May 12, 2026, 3:18 p.m. |
| PDg | Predicate description generation | batch_6a0345400778819081fb3b5b71336cd7 |
completed | May 12, 2026, 3:20 p.m. |
Created at: May 3, 2026, 4:16 p.m.