Triple
T24983455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FDNY Ladder 81 |
E625235
|
entity |
| Predicate | typeOfFireServiceUnit |
P137580
|
FINISHED |
| Object | truck company |
—
|
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: truck company | Statement: [FDNY Ladder 81, typeOfFireServiceUnit, truck company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFireServiceUnit Context triple: [FDNY Ladder 81, typeOfFireServiceUnit, truck company]
-
A.
typeOfEmergencyService
Indicates the specific category or kind of emergency service associated with or provided in a given situation.
-
B.
hasTypeOfApparatus
chosen
Indicates that one entity is associated with, or utilizes, a specific kind or category of apparatus.
-
C.
hasFireAndRescueServiceCategory
Indicates the specific fire and rescue service classification or category assigned to an entity, such as a building, facility, or site.
-
D.
hasFireServicesFrom
Indicates that one entity receives fire protection or firefighting services from another entity.
-
E.
typeOfFrontierUnit
Indicates that one unit is classified as a specific type or category of frontier unit in relation to another.
- 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_69e2ff254570819093d197b1900305ac |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f66598d6008190a7ca8ff80399fd34 |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 18, 2026, 6:02 a.m.