Triple
T4072451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Marshall (British Army officer) |
E86677
|
entity |
| Predicate | hasGivenName |
P17
|
FINISHED |
| Object | William |
E772
|
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: William | Statement: [William Marshall (British Army officer), hasGivenName, William]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Context triple: [William Marshall (British Army officer), hasGivenName, William]
-
A.
William
chosen
William is a common masculine given name of Germanic origin, widely used in English-speaking countries.
-
B.
Thomas
Thomas is the given name of Thomas Cranmer, the 16th-century Archbishop of Canterbury and a leading figure in the English Reformation.
-
C.
Thomas
Thomas is a common masculine given name of Aramaic origin, widely used in English-speaking and many other cultures.
-
D.
Thomas
Thomas is the birth name of the Scottish actor better known as Sean Connery, the original cinematic James Bond.
-
E.
Thomas
Thomas is the given first name of Boston Corbett, the Union Army soldier known for killing Abraham Lincoln’s assassin, John Wilkes Booth.
- 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_69aed93ebe448190a1f1686e28740ac9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc22be988190a2b6575d4f5e0f7b |
completed | March 9, 2026, 4:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b562b99e84819085e1616fb9a61465 |
completed | March 14, 2026, 1:29 p.m. |
Created at: March 9, 2026, 3:38 p.m.