Triple
T29324340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The John Stevens Shop |
E743601
|
entity |
| Predicate | hasNotableCraftsman |
P118614
|
FINISHED |
| Object |
John Howard Benson
John Howard Benson was a prominent American stone carver, calligrapher, and designer renowned for his influential work in lettering and inscriptions in the early 20th century.
|
E1863109
|
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: John Howard Benson | Statement: [The John Stevens Shop, hasNotableCraftsman, John Howard Benson]
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: John Howard Benson Triple: [The John Stevens Shop, hasNotableCraftsman, John Howard Benson]
Generated description
John Howard Benson was a prominent American stone carver, calligrapher, and designer renowned for his influential work in lettering and inscriptions in the early 20th century.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableCraftsman Context triple: [The John Stevens Shop, hasNotableCraftsman, John Howard Benson]
-
A.
hasCraftsman
Indicates that one entity serves as the craftsman, maker, or artisan responsible for creating, building, or crafting another entity.
-
B.
hasNotableCraft
Indicates that an entity is associated with a particularly significant or distinguished craft, skill, or artisanal practice.
-
C.
associatedCraftsmen
chosen
Indicates that there is a relationship linking an entity to one or more craftsmen who are connected to it through work, creation, or service.
-
D.
hasCraftsmanGod
Indicates that an entity has an associated deity specifically responsible for craftsmanship or artisan skills.
-
E.
employedCraftsmenFrom
Indicates that one entity has hired or utilizes craftsmen originating from another entity.
- 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_69f09125f784819080f4e9fce9fe624f |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69ffaa7bc45c8190b907db8579244a7b |
completed | May 9, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a25a87445388190841a05393959b777 |
completed | June 7, 2026, 5:20 p.m. |
| NEDg | Description generation | batch_6a25ac6034a081909518662153fbe1b3 |
completed | June 7, 2026, 5:37 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a25b13b60088190bfe08fd65547a593 |
completed | June 7, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69ffa9f6c9a481908fbd4d18b311cbe2 |
completed | May 9, 2026, 9:41 p.m. |
Created at: April 28, 2026, 1:25 p.m.