Triple
T36301704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heart of Stone |
E893833
|
entity |
| Predicate | characterPlayedByGalGadot |
P200830
|
FINISHED |
| Object | Rachel Stone |
—
|
NE NERFINISHED |
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: Rachel Stone | Statement: [Heart of Stone, characterPlayedByGalGadot, Rachel Stone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterPlayedByGalGadot Context triple: [Heart of Stone, characterPlayedByGalGadot, Rachel Stone]
-
A.
characterPlayedByCariceVanHouten
Indicates that the subject is a character portrayed by the actress Carice van Houten.
-
B.
characterPlayedBy Emmanuelle Chriqui
Indicates that the role or character in question is portrayed or acted by Emmanuelle Chriqui.
-
C.
characterPlayedBy Larisa Oleynik
Indicates that a specific fictional character is portrayed or acted by Larisa Oleynik.
-
D.
roleOfGueneverePlayedBy
Indicates that a specified person or performer portrays the character Guenevere in a production or performance.
-
E.
characterPlayedByEmilyBlunt
Indicates that the subject is a character portrayed by the actress Emily Blunt.
- F. None of above. chosen
Provenance (4 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_69f76e4c1b248190b10667d0213537fe |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ffb1218cb08190a814c7f0833501a7 |
completed | May 9, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69ffb083d6988190b2757e0cfd629b75 |
completed | May 9, 2026, 10:09 p.m. |
| PDg | Predicate description generation | batch_69ffb120b9988190b6361c69265033c0 |
completed | May 9, 2026, 10:11 p.m. |
Created at: May 3, 2026, 4:09 p.m.