Triple
T15917394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Tirad Pass |
E386003
|
entity |
| Predicate | forceSizeAmerican |
P49546
|
FINISHED |
| Object | several hundred soldiers |
—
|
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: several hundred soldiers | Statement: [Battle of Tirad Pass, forceSizeAmerican, several hundred soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forceSizeAmerican Context triple: [Battle of Tirad Pass, forceSizeAmerican, several hundred soldiers]
-
A.
forceTypeAmerican
Indicates that the force involved is of the American (United States) military or security type.
-
B.
forceSize
chosen
Indicates a relationship where one entity specifies or constrains the magnitude or size of a force associated with another entity.
-
C.
forceSizeConfederate
Indicates that one entity compels or influences another (the confederate) to adopt or present a particular physical size or size-related appearance.
-
D.
forceSizeUnion
Indicates that the combined size or extent of multiple entities is being constrained or determined as a single unified whole.
-
E.
sizeDescription
Indicates a relationship where one entity provides descriptive information about the size or scale of another entity.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e172b48b308190bc430b2308cbc75b |
completed | April 16, 2026, 11:37 p.m. |
| PD | Predicate disambiguation | batch_69e142cf5c548190a931f7b58144cd31 |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:52 a.m.