Triple
T4904737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nathan |
E109886
|
entity |
| Predicate | proclaimedAt |
P430
|
FINISHED |
| Object | Gihon |
E464108
|
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: Gihon | Statement: [Nathan, proclaimedAt, Gihon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gihon Context triple: [Nathan, proclaimedAt, Gihon]
-
A.
Gihon Spring
chosen
Gihon Spring is an ancient freshwater source in Jerusalem, historically vital as the city’s main water supply and central to its early settlement and defenses.
-
B.
Kishon River
The Kishon River is a major watercourse in northern Israel that flows from the Jezreel Valley to the Mediterranean Sea near Haifa.
-
C.
Banias River
The Banias River is a major spring-fed stream in the Golan Heights that forms one of the principal headwaters of the Jordan River.
-
D.
Pishon
Pishon is one of the four rivers mentioned in the biblical Book of Genesis as flowing from the Garden of Eden.
-
E.
Samaria stream
Samaria stream is a mountain river running through the Samaria Gorge on the island of Crete, shaping its dramatic landscape and supporting its unique ecosystem.
- 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_69bd441180708190ba42ffb44fea533a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e71a5c481909f5862bf497c3c9d |
completed | March 20, 2026, 3:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be6fdaaf588190a180d0bf5979c2d2 |
completed | March 21, 2026, 10:15 a.m. |
Created at: March 20, 2026, 1:29 p.m.