Triple
T32427301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ES-125 |
E828610
|
entity |
| Predicate | factory |
P19019
|
FINISHED |
| Object |
Gibson Kalamazoo plant
The Gibson Kalamazoo plant was the historic Michigan factory where Gibson produced many of its classic guitars and other instruments throughout much of the 20th century.
|
E2006789
|
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: Gibson Kalamazoo plant | Statement: [ES-125, factory, Gibson Kalamazoo plant]
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: Gibson Kalamazoo plant Triple: [ES-125, factory, Gibson Kalamazoo plant]
Generated description
The Gibson Kalamazoo plant was the historic Michigan factory where Gibson produced many of its classic guitars and other instruments throughout much of the 20th century.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: factory Context triple: [ES-125, factory, Gibson Kalamazoo plant]
-
A.
factoryBuilt
Indicates that one entity constructed or established a factory for or at the location of another entity.
-
B.
facility
chosen
Indicates that one entity is a building, installation, or physical infrastructure used to host, support, or enable the operations or activities of another entity.
-
C.
factor
Indicates that one entity is a contributing cause, influence, or component affecting the state, outcome, or existence of another entity.
-
D.
productionFacilityType
Indicates the specific kind or category of facility where production or manufacturing activities take place.
-
E.
afirma
Indicates that one entity asserts, claims, or states something about another entity or a proposition as being true.
- 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_69f3491b28bc8190b75cea7a507f337b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c2a85d4c81909c399aaecc7c440b |
completed | May 3, 2026, 3:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a344f2af0b481909f7c8001801ea1d4 |
completed | June 18, 2026, 8:03 p.m. |
| NEDg | Description generation | batch_6a3451efcc088190971fcde8e42ac9a0 |
completed | June 18, 2026, 8:15 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a345f7387508190853808812475575f |
completed | June 18, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69f6ba6eb32c8190bf405b2011fa48f7 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:54 a.m.