Triple
T19793913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wilkes-Barre Fire Department |
E475488
|
entity |
| Predicate | hasCallType |
P29529
|
FINISHED |
| Object | structure fires |
—
|
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: structure fires | Statement: [Wilkes-Barre Fire Department, hasCallType, structure fires]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCallType Context triple: [Wilkes-Barre Fire Department, hasCallType, structure fires]
-
A.
hasCall
Indicates that one entity initiates or participates in a telephone or voice communication with another entity.
-
B.
callType
chosen
Indicates the category or nature of a call (such as its purpose, direction, or handling), distinguishing one kind of call from another.
-
C.
hasCallInNumber
Indicates that an entity has an associated telephone number designated for receiving incoming calls.
-
D.
hasCallLine
Indicates that there is a specific telephone or communication line associated with or used for a particular call.
-
E.
operatesOnCallNumberType
Indicates that an entity performs operations specifically on items identified by a particular call number type.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c5a7d48190b2a384f768d13750 |
completed | April 20, 2026, 4:26 p.m. |
| PD | Predicate disambiguation | batch_69e5305858108190bbbfdb9ba3ab9f80 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:49 p.m.