Triple
T18968555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warren’s Shaft system |
E464104
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Charles Warren |
—
|
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: Charles Warren | Statement: [Warren’s Shaft system, namedAfter, Charles Warren]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Warren Context triple: [Warren’s Shaft system, namedAfter, Charles Warren]
-
A.
Charles Warren
chosen
Charles Warren was a 19th-century British army officer and pioneering archaeologist best known for his early excavations in Jerusalem and contributions to biblical archaeology.
-
B.
John Coveny
John Coveny is a television producer and writer best known as the co-creator and executive producer of the crime drama series "Longmire."
-
C.
Henry Warren
Henry Warren is a fictional character appearing in the novel "The Bone Garden."
-
D.
John Van Ness
John Van Ness was an early 19th-century American politician and public figure associated with the development and civic life of Washington, D.C.
-
E.
William J. Worthington
William J. Worthington is a notable individual associated with the Worthington name, recognized for his prominence in historical or public records.
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6172888819090a8b3cb1db20496 |
completed | April 20, 2026, 7:30 a.m. |
Created at: April 10, 2026, noon