Triple
T7564346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Taylor |
E178873
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Maria Burton |
E674073
|
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: Maria Burton | Statement: [Elizabeth Taylor, child, Maria Burton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maria Burton Context triple: [Elizabeth Taylor, child, Maria Burton]
-
A.
Maria Burton
chosen
Maria Burton is a relatively obscure individual whose name alone does not clearly identify a widely known public figure or notable background.
-
B.
Maria Burton
Maria Burton is the adopted daughter of legendary British-American actress Elizabeth Taylor and her fifth husband, producer Mike Todd.
-
C.
Victoria Burton
Victoria Burton is known as the wife of Scottish actor and comedian Gregor Fisher.
-
D.
Jessica Burton
Jessica Burton is a daughter of the acclaimed Welsh actor Richard Burton.
-
E.
Emily Williamson
Emily Williamson was a pioneering British conservationist who co-founded what became the Royal Society for the Protection of Birds, helping launch the modern bird protection movement.
- 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_69c69f2f80288190b95cceb4da92ab2b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f8fc6a408190abf363a29359e764 |
completed | March 27, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8615c98808190a9dd598846a598b2 |
completed | March 28, 2026, 11:16 p.m. |
Created at: March 27, 2026, 3:50 p.m.