Triple
T32732779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 823 RED HORSE |
E836997
|
entity |
| Predicate | RED HORSEExpansion |
P174746
|
FINISHED |
| Object |
Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers
Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers (RED HORSE) are specialized U.S. Air Force civil engineering units trained to rapidly deploy worldwide to construct, repair, and maintain airfields and other critical infrastructure in austere or contingency environments.
|
E2018020
|
NE FINISHED |
How this triple was built (3 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: Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers | Statement: [823 RED HORSE, RED HORSEExpansion, Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers Triple: [823 RED HORSE, RED HORSEExpansion, Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers]
Generated description
Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers (RED HORSE) are specialized U.S. Air Force civil engineering units trained to rapidly deploy worldwide to construct, repair, and maintain airfields and other critical infrastructure in austere or contingency environments.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RED HORSEExpansion Context triple: [823 RED HORSE, RED HORSEExpansion, Rapid Engineer Deployable Heavy Operational Repair Squadron Engineers]
-
A.
remnantExpansion
Indicates that a remaining part or leftover portion of something grows, spreads, or extends beyond its original bounds.
-
B.
expansionPack
Indicates that one item serves as an add-on or supplementary content package that extends the features or scope of another item.
-
C.
hordeNewRace
Indicates that a new race is being added to or associated with the Horde faction.
-
D.
hasExpansion
Indicates that one entity serves as a larger, extended, or elaborated form of another entity.
-
E.
introducedInExpansion
Indicates that something (such as a feature, item, or concept) was first added or made available as part of a specific expansion.
- F. None of above. chosen
Provenance (7 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_69f34935fb048190ad4967420581f835 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c9013da48190915619e554f079ff |
completed | May 3, 2026, 4:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a349edcb3708190a668ce20a12a5a6f |
completed | June 19, 2026, 1:43 a.m. |
| NEDg | Description generation | batch_6a349f8044248190bb242457861c365e |
completed | June 19, 2026, 1:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a349fcf783881909cb072d0bbdbfce9 |
completed | June 19, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f717a88190a924d614c2c9bca3 |
completed | May 3, 2026, 3:41 a.m. |
| PDg | Predicate description generation | batch_69f6c5fa10dc8190b2c06e4c701bd246 |
completed | May 3, 2026, 3:50 a.m. |
Created at: May 1, 2026, 1:11 a.m.