Triple
T14987165
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eirene |
E373734
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Dike |
E147131
|
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: Dike | Statement: [Eirene, sibling, Dike]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dike Context triple: [Eirene, sibling, Dike]
-
A.
Dike
chosen
Dike is the Greek goddess of justice and moral order, often depicted as a guardian of human righteousness and fairness.
-
B.
Snake Dike
Snake Dike is a classic, runout slab and dike rock climbing route on the southwest face of Half Dome in Yosemite National Park.
-
C.
Great Dyke
The Great Dyke is a major linear geological feature in Zimbabwe rich in mineral deposits, notably chromium and platinum group metals.
-
D.
Rhine dike
The Rhine dike is a protective embankment along the Rhine River designed to prevent flooding and manage water levels in adjacent low-lying areas.
-
E.
Dike Kokaral
Dike Kokaral is a man-made dam in Kazakhstan built to restore and stabilize water levels in the North Aral Sea.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7007588819095bb1de029a6f2eb |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe8c036bfc8190b01bf2128403f557 |
completed | May 9, 2026, 1:21 a.m. |
Created at: April 10, 2026, 2:52 a.m.