Triple
T10724560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kedemah |
E252905
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Naphish |
E252904
|
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: Naphish | Statement: [Kedemah, sibling, Naphish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Naphish Context triple: [Kedemah, sibling, Naphish]
-
A.
Naphish
chosen
Naphish is a minor biblical figure listed among the descendants of Ishmael in the Hebrew Bible.
-
B.
Merenkahre
Merenkahre is an ancient Egyptian pharaoh character in the "Night at the Museum" film series, depicted as the father of Ahkmenrah.
-
C.
Abnub
Abnub is a city in Upper Egypt situated within the Asyut Governorate, known primarily as a local administrative and population center in the region.
-
D.
Tahawus
Tahawus is a remote hamlet in New York’s Adirondack Mountains known for its historic iron mining operations and proximity to High Peaks wilderness areas.
-
E.
Asungor
Asungor is an alternative name for the Sungor language, a Nilo-Saharan language spoken by the Sungor people of Chad and Sudan.
- 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_69d6aa5d8be481909a43218b2bfdbe95 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d70d473cfc8190b0ea6dbec14ee070 |
completed | April 9, 2026, 2:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69deb08d63d481908ab1d5038424dab6 |
completed | April 14, 2026, 9:24 p.m. |
Created at: April 8, 2026, 9:14 p.m.