Triple
T13003326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Hare |
E322223
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Hare |
E907504
|
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: Hare | Statement: [David Hare, familyName, Hare]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hare Context triple: [David Hare, familyName, Hare]
-
A.
Hare
chosen
Hare is a common English surname borne by various notable individuals across fields such as politics, religion, and the arts.
-
B.
Rabbit
Rabbit Maranville was a Hall of Fame Major League Baseball shortstop known for his exceptional fielding, durability, and colorful personality in the early 20th century.
-
C.
Rabbit
Rabbit is a famous stainless-steel sculpture by Jeff Koons, celebrated as an iconic work of contemporary pop and conceptual art.
-
D.
Rabbit
Rabbit is a fussy, practical, and often bossy animal character from A. A. Milne’s Winnie-the-Pooh stories, known for trying to keep order in the Hundred Acre Wood.
-
E.
Rabbit
Rabbit is a high-speed stream cipher designed for efficient software implementation, particularly suited for environments with limited resources.
- 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_69d807657e8c8190bd9435ee2f823845 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d97e9a2a448190968833354280e474 |
completed | April 10, 2026, 10:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6c103e49c8190a140527f24b5c799 |
completed | May 3, 2026, 3:29 a.m. |
Created at: April 9, 2026, 8:47 p.m.