Triple
T3629621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Illyrians |
E76922
|
entity |
| Predicate | mentionedBy |
P831
|
FINISHED |
| Object | Appian |
E212508
|
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: Appian | Statement: [Illyrians, mentionedBy, Appian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Appian Context triple: [Illyrians, mentionedBy, Appian]
-
A.
Appian
chosen
Appian was a 2nd-century AD Roman historian of Greek origin best known for his multi-volume work "Roman History," which includes a detailed account of the Roman civil wars.
-
B.
Appirio
Appirio is a cloud services and consulting company known for helping enterprises implement and optimize platforms like Salesforce and Workday.
-
C.
Fieldsights
Fieldsights is an online publication platform of the Society for Cultural Anthropology featuring essays, interviews, and multimedia on contemporary anthropological issues.
-
D.
Power Apps
Power Apps is a Microsoft low-code development platform that enables users to quickly build and deploy custom business applications across web and mobile.
-
E.
Gainsight
Gainsight is a customer success and product experience software company known for helping businesses reduce churn, drive expansion, and improve customer retention through data-driven insights and workflows.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad85dc03948190b35b7189e4175bcc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc300223881909019982ebf194f78 |
completed | March 8, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b43328931881908bd92cb32a366e93 |
completed | March 13, 2026, 3:54 p.m. |
Created at: March 8, 2026, 3:23 p.m.