Triple
T3968325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Waterboy |
E92268
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Fairuza Balk |
E161342
|
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: Fairuza Balk | Statement: [The Waterboy, starring, Fairuza Balk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fairuza Balk Context triple: [The Waterboy, starring, Fairuza Balk]
-
A.
Fairuza Balk
chosen
Fairuza Balk is an American actress known for her intense, offbeat roles in films such as "The Craft," "American History X," and "Almost Famous."
-
B.
Ayda Sirhan
Ayda Sirhan is a family member of Munir Sirhan, who is known as the brother of Sirhan Sirhan, the assassin of Robert F. Kennedy.
-
C.
Martika
Martika is an American pop singer and former child actress best known for her late-1980s hits like "Toy Soldiers."
-
D.
Gianna Nannini
Gianna Nannini is an Italian rock singer-songwriter renowned for her powerful voice and international hit collaborations, including the official song of the 1990 FIFA World Cup.
-
E.
Dalida
Dalida was a hugely popular French-Italian-Egyptian singer and actress known for her multilingual hits and enduring influence on European and Middle Eastern pop music.
- 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_69aed96624188190ac8c45bb57ab72b5 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef978a14c8190a7982a2e4489b6ea |
completed | March 9, 2026, 4:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b533c189a88190b3a81c63621b98ac |
completed | March 14, 2026, 10:09 a.m. |
Created at: March 9, 2026, 3:32 p.m.