Triple
T31381902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 155th Air Refueling Wing |
E800481
|
entity |
| Predicate | primarySquadron |
P13144
|
FINISHED |
| Object | 173rd Air Refueling Squadron |
E1960723
|
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: 173rd Air Refueling Squadron | Statement: [155th Air Refueling Wing, primarySquadron, 173rd Air Refueling Squadron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primarySquadron Context triple: [155th Air Refueling Wing, primarySquadron, 173rd Air Refueling Squadron]
-
A.
squadron
chosen
Indicates that an entity is organized into or associated with a specific squadron as a formal operational unit.
-
B.
squadronCode
Indicates the identifying code assigned to a military or aviation squadron that denotes its unit designation.
-
C.
squadronSystem
Indicates a relationship where an entity functions as or is part of the system, organization, or structure associated with a particular squadron.
-
D.
squadronRole
Indicates the specific function or duty an entity has within a squadron or organized group of units.
-
E.
squadronSize
Indicates the number of units or members that make up a particular squadron.
- F. None of above.
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_69f224e84da08190abfc2f17494a33c8 |
completed | April 29, 2026, 3:34 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2b076887d88190b3144b91bc7215d2 |
completed | June 11, 2026, 7:07 p.m. |
| PD | Predicate disambiguation | batch_6a0379e5174c8190a0bdde7e381b7624 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 9:19 p.m.