Triple
T31025183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Habu missions |
E790548
|
entity |
| Predicate | baseCodeName |
P125312
|
FINISHED |
| Object |
OL-8 (Operating Location 8)
OL-8 (Operating Location 8) was a covert U.S. Air Force operating site associated with the SR-71 “Habu” reconnaissance program.
|
E1943847
|
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: OL-8 (Operating Location 8) | Statement: [Habu missions, baseCodeName, OL-8 (Operating Location 8)]
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: OL-8 (Operating Location 8) Triple: [Habu missions, baseCodeName, OL-8 (Operating Location 8)]
Generated description
OL-8 (Operating Location 8) was a covert U.S. Air Force operating site associated with the SR-71 “Habu” reconnaissance program.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baseCodeName Context triple: [Habu missions, baseCodeName, OL-8 (Operating Location 8)]
-
A.
usesCodeName
Indicates that one entity refers to another entity by a code name or alias instead of its real or full designation.
-
B.
testCodeName
Indicates that an entity is identified or referred to by a specific test code name.
-
C.
endUseAsCodename
Indicates that an entity stops being used as a codename for another entity or concept.
-
D.
relatedCodename
Indicates that one entity has an associated or connected codename that is contextually related to it.
-
E.
codenameComponent
chosen
Indicates that one entity serves as the codename or code-designation assigned to another entity as its component or identifying label.
- F. None of above.
Provenance (6 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_69f224c811508190a7de096a5b1f5798 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a291846c2488190a472ce91eb2d0c83 |
completed | June 10, 2026, 7:54 a.m. |
| NEDg | Description generation | batch_6a291c980a1881908f8bd99eea8b7383 |
completed | June 10, 2026, 8:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a291d4ed5b88190b613ce7f759c0baf |
completed | June 10, 2026, 8:16 a.m. |
| PD | Predicate disambiguation | batch_69f690ef92308190903a54fc74233269 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 29, 2026, 8:58 p.m.