Triple
T5751440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doug Liman |
E126860
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Fair Game |
E530221
|
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: Fair Game | Statement: [Doug Liman, directed, Fair Game]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fair Game Context triple: [Doug Liman, directed, Fair Game]
-
A.
Fair Game
chosen
Fair Game is a 2010 political thriller film about CIA operative Valerie Plame and the outing of her covert identity, co-written by screenwriter John-Henry Butterworth.
-
B.
Fair Game (novel)
Fair Game is a 1974 thriller novel by Paula Gosling, best known as the source material for multiple film adaptations, including the 1986 Sylvester Stallone movie "Cobra."
-
C.
Caught in the Game
Caught in the Game is a 1983 hard rock album by American band Survivor, known for its melodic rock sound and powerful vocals.
-
D.
The Name of the Game
"The Name of the Game" is a 1977 pop song by Swedish group ABBA, known for its melodic complexity and introspective lyrics.
-
E.
The Name of the Game
The Name of the Game is an American television series from the late 1960s and early 1970s that followed the lives of magazine publishing executives through rotating lead characters and storylines.
- 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_69c00832aedc81909899801b141fa3b4 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0288a0ea8819091ac6f965471ceee |
completed | March 22, 2026, 5:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0a167f2508190a8dd507f237e771b |
completed | March 23, 2026, 2:11 a.m. |
Created at: March 22, 2026, 3:48 p.m.