Triple
T2177910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Z. Foster |
E48573
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Foster |
E25127
|
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: Foster | Statement: [William Z. Foster, familyName, Foster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Foster Context triple: [William Z. Foster, familyName, Foster]
-
A.
Foster
chosen
Foster is a common English surname borne by numerous notable individuals across fields such as entertainment, sports, politics, and academia.
-
B.
Fay
Fay is a given name most famously associated with Canadian-American actress Fay Wray, the iconic star of the 1933 film "King Kong."
-
C.
Foy
Foy is a vain and arrogant dandy in the comedy film "A Million Ways to Die in the West," serving as the smug romantic rival to the protagonist.
-
D.
Foege
Foege is the surname of William H. Foege, an American epidemiologist renowned for his pivotal role in the global eradication of smallpox.
-
E.
Hollis
Hollis is the surname of American hip-hop producer and rapper Hit-Boy, known for crafting chart-topping tracks for major artists across the genre.
- 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_69a88aa3faa48190995b233af6525815 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbeee0a988190b0729f9070aa4503 |
completed | March 7, 2026, 6 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5da14e3881909f0beda339599938 |
completed | March 9, 2026, 5:41 a.m. |
Created at: March 4, 2026, 7:45 p.m.