Triple
T5809309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Na San |
E128825
|
entity |
| Predicate | airfieldRole |
P66457
|
FINISHED |
| Object | Na San airstrip used as logistical hub |
—
|
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: Na San airstrip used as logistical hub | Statement: [Battle of Na San, airfieldRole, Na San airstrip used as logistical hub]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airfieldRole Context triple: [Battle of Na San, airfieldRole, Na San airstrip used as logistical hub]
-
A.
airportRole
Indicates that an entity serves a specific functional role or capacity within the context of an airport.
-
B.
aircraftFacility
Indicates that a facility is designed, equipped, or used to support the operation, maintenance, or accommodation of aircraft.
-
C.
containsAirfield
Indicates that a location or area includes at least one airfield within its boundaries.
-
D.
airfieldDefended
Indicates that defensive measures or forces are in place to protect an airfield from attack or unauthorized intrusion.
-
E.
hasAirfieldType
Indicates that an airfield is classified as having a particular type or category of airfield.
- 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_69c0084788848190bcf71f6bc5d71597 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02b1867a481909a7ea3331dbb04ce |
completed | March 22, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69c021d5ecd081908a62dd66e26f8598 |
completed | March 22, 2026, 5:07 p.m. |
| PDg | Predicate description generation | batch_69c028ffe180819099e084fe557e789c |
completed | March 22, 2026, 5:38 p.m. |
Created at: March 22, 2026, 3:52 p.m.