Triple
T9102207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boconnoc, Cornwall |
E218385
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Thomas Pitt |
E218384
|
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: Thomas Pitt | Statement: [Boconnoc, Cornwall, associatedWith, Thomas Pitt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Pitt Context triple: [Boconnoc, Cornwall, associatedWith, Thomas Pitt]
-
A.
Thomas Pitt
chosen
Thomas Pitt was a prominent member of the influential Pitt family, known for his role in British political and social life.
-
B.
Raymond Shaw
Raymond Shaw is the brainwashed Korean War veteran and Medal of Honor recipient whose programmed assassination role drives the political thriller plot of "The Manchurian Candidate."
-
C.
Inspector Lonergan
Inspector Lonergan is a fictional police inspector featured in the 1932 mystery film "The Night Club Lady."
-
D.
Charles Lenox
Charles Lenox was a prominent landowner and early benefactor after whom the town of Lenox, Massachusetts, was named.
-
E.
Henry Tucker
Henry Tucker was a Bermudian politician who became the territory's first premier and played a key role in modernizing its political and economic landscape.
- 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_69ca83db7448819090d0a5de842ef2ac |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc971435d08190b5007ed44ac0a364 |
completed | April 1, 2026, 3:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0182d8ea08190b4337a77b47019a5 |
completed | April 3, 2026, 7:42 p.m. |
Created at: March 30, 2026, 7:15 p.m.