Triple
T9763839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chief Master-at-Arms (USCG E-9 ranks) |
E236733
|
entity |
| Predicate | typicalBillet |
P90904
|
FINISHED |
| Object | senior enlisted leader for security |
—
|
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: senior enlisted leader for security | Statement: [Chief Master-at-Arms (USCG E-9 ranks), typicalBillet, senior enlisted leader for security]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalBillet Context triple: [Chief Master-at-Arms (USCG E-9 ranks), typicalBillet, senior enlisted leader for security]
-
A.
typicalTicketText
Indicates that the associated text represents the standard or commonly used wording for a ticket.
-
B.
typicalEvent
Indicates that the associated event is a common, characteristic, or prototypical occurrence for the given entity or situation.
-
C.
ticketFormat
Indicates the specific structure, layout, or template in which a ticket is represented or issued.
-
D.
ticket
Indicates that an entity serves as or is associated with a ticket, typically representing authorization, access, or a record for an event, service, or transaction.
-
E.
ticketTypeExample
Indicates that an entity serves as an example or illustrative instance of a particular ticket type.
- F. None of above. chosen
Provenance (4 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_69ca84d64f6c8190a4ed4e9f5936eda5 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda09ed54c8190a5879e14184cddf4 |
completed | April 1, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69cd03d0772c8190bd1750cf1cfba309 |
completed | April 1, 2026, 11:38 a.m. |
| PDg | Predicate description generation | batch_69cd081a9c5c819093439be7e802ff85 |
completed | April 1, 2026, 11:57 a.m. |
Created at: March 30, 2026, 8:25 p.m.