Triple
T15856730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colleen Ahland |
E384477
|
entity |
| Predicate | hasPublishedOnTopic |
P46966
|
FINISHED |
| Object | phonology of Koman languages |
—
|
LITERAL 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: phonology of Koman languages | Statement: [Colleen Ahland, hasPublishedOnTopic, phonology of Koman languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPublishedOnTopic Context triple: [Colleen Ahland, hasPublishedOnTopic, phonology of Koman languages]
-
A.
hasPublishedOn
chosen
Indicates that an entity (such as an author or publisher) has released or made content publicly available on a particular platform, medium, or date.
-
B.
hasPublication
Indicates that an entity is associated with or responsible for a specific publication.
-
C.
publishesOnTopic
Indicates that an entity (such as a person or organization) produces and releases content whose subject matter concerns a specified topic.
-
D.
hasPub
Indicates that an entity is associated with, or has access to, a public house (pub) as a related establishment or feature.
-
E.
hasExcerptsPublishedOn
Indicates that certain excerpts from a work or content have been published on a specified platform, medium, or outlet.
- 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_69d86da422088190aac39e32e6c68429 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e174de2cd48190ab18e48c9f051a2a |
completed | April 16, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69e142b976c081908d3ba3e705419f3a |
completed | April 16, 2026, 8:12 p.m. |
Created at: April 10, 2026, 4:50 a.m.