Triple
T29163955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Photographic Sketch Book of the War |
E739262
|
entity |
| Predicate | hasCaptionTextBy |
P81389
|
FINISHED |
| Object | Alexander Gardner |
—
|
NE NERFINISHED |
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: Alexander Gardner | Statement: [Photographic Sketch Book of the War, hasCaptionTextBy, Alexander Gardner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCaptionTextBy Context triple: [Photographic Sketch Book of the War, hasCaptionTextBy, Alexander Gardner]
-
A.
hasTextBy
chosen
Indicates that one entity (such as a document, work, or record) contains or is associated with text authored or written by another entity.
-
B.
hasText
Indicates that an entity is associated with or contains a specific piece of textual content.
-
C.
hasTitleIn
Indicates that an entity holds or is associated with a specific title within a particular context, domain, or language.
-
D.
hasOnScreenText
Indicates that some text content is visually displayed on a screen within a given context or medium.
-
E.
hasTitleOf
Indicates that one entity holds, bears, or is designated by the official title, name, or rank specified by 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_69f07cb528fc8190a556b73990c347c8 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69fd509e6bc08190b263923c2f40fea3 |
completed | May 8, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69fd4fd1a58881909d4b84de1b24e380 |
completed | May 8, 2026, 2:52 a.m. |
Created at: April 28, 2026, 11:49 a.m.