Triple
T19497167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apis |
E487798
|
entity |
| Predicate | egyptianName |
P8488
|
FINISHED |
| Object | Hapi |
—
|
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: Hapi | Statement: [Apis, egyptianName, Hapi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hapi Context triple: [Apis, egyptianName, Hapi]
-
A.
Hapi
Hapi is a rich, configuration-centric Node.js web framework designed for building scalable, modular server-side applications and APIs.
-
B.
Hapi
chosen
Hapi is the ancient Egyptian god of the annual Nile inundation, symbolizing fertility, abundance, and the life-giving power of the river.
-
C.
Hap
Hap is the nickname of Henry "Hap" Arnold, a pioneering U.S. Army Air Forces general and key architect of American air power during World War II.
-
D.
Hap
Hap is a supporting character in the 1989 romantic fantasy film "Always," which centers on a deceased pilot who returns as a spirit to guide the living.
-
E.
Hap
Hap was a notable racehorse associated with prominent American businessman and Thoroughbred owner Allen E. Paulson.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e634924e24819085cd61ba33c84570 |
completed | April 20, 2026, 2:13 p.m. |
Created at: April 10, 2026, 1:40 p.m.