Triple
T34781405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Part III (section of "Howl") |
E1002670
|
entity |
| Predicate | firstPublicationPublisher |
P7323
|
FINISHED |
| Object | City Lights Books |
E38235
|
NE FINISHED |
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: City Lights Books | Statement: [Part III (section of "Howl"), firstPublicationPublisher, City Lights Books]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPublicationPublisher Context triple: [Part III (section of "Howl"), firstPublicationPublisher, City Lights Books]
-
A.
firstPublisher
chosen
Indicates that an entity is the original or earliest publisher of another entity (such as a work, edition, or resource).
-
B.
publisherOfFirstFullPublication
Indicates that the subject is the publisher responsible for the first full publication of the object.
-
C.
firstCompleteEditionPublisher
Indicates the publisher responsible for issuing the first complete edition of a work.
-
D.
originalPublisherType
Indicates the type or category of the entity that first published or released the content.
-
E.
firstPublicationIn
Indicates the initial venue, medium, or context in which a work was first published.
- F. None of above.
Provenance (4 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_69f76db30a108190bb57ca95b873e5bb |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a376642e6708190aa64aa53544c7350 |
completed | June 21, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 3:59 p.m.