Triple
T18334369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Tasker |
E439229
|
entity |
| Predicate | primaryAntagonist |
P4675
|
FINISHED |
| Object |
Salim Abu Aziz
Salim Abu Aziz is the main terrorist villain in the 1994 action film "True Lies," serving as the primary adversary to Arnold Schwarzenegger’s character, Harry Tasker.
|
E1319758
|
NE FINISHED |
How this triple was built (4 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: Salim Abu Aziz | Statement: [Harry Tasker, primaryAntagonist, Salim Abu Aziz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salim Abu Aziz Context triple: [Harry Tasker, primaryAntagonist, Salim Abu Aziz]
-
A.
Salah Abu Seif
Salah Abu Seif was a pioneering Egyptian film director widely regarded as the father of realism in Egyptian cinema.
-
B.
Hussein Amer
Hussein Amer is an individual notable enough to be recognized as a prominent bearer of the surname Amer.
-
C.
Zaki Salam
Zaki Salam is a notable individual recognized as a distinguished bearer of the surname Salam.
-
D.
Mohammad Salameh
Mohammad Salameh is a Palestinian terrorist best known as one of the main conspirators in the 1993 World Trade Center bombing in New York City.
-
E.
Nawaf Salam
Nawaf Salam is a Lebanese diplomat, jurist, and former UN ambassador who serves as President of the International Court of Justice.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Salim Abu Aziz Triple: [Harry Tasker, primaryAntagonist, Salim Abu Aziz]
Generated description
Salim Abu Aziz is the main terrorist villain in the 1994 action film "True Lies," serving as the primary adversary to Arnold Schwarzenegger’s character, Harry Tasker.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Salim Abu Aziz Target entity description: Salim Abu Aziz is the main terrorist villain in the 1994 action film "True Lies," serving as the primary adversary to Arnold Schwarzenegger’s character, Harry Tasker.
-
A.
Salah Abu Seif
Salah Abu Seif was a pioneering Egyptian film director widely regarded as the father of realism in Egyptian cinema.
-
B.
Hussein Amer
Hussein Amer is an individual notable enough to be recognized as a prominent bearer of the surname Amer.
-
C.
Zaki Salam
Zaki Salam is a notable individual recognized as a distinguished bearer of the surname Salam.
-
D.
Mohammad Salameh
Mohammad Salameh is a Palestinian terrorist best known as one of the main conspirators in the 1993 World Trade Center bombing in New York City.
-
E.
Nawaf Salam
Nawaf Salam is a Lebanese diplomat, jurist, and former UN ambassador who serves as President of the International Court of Justice.
- F. None of above. chosen
Provenance (5 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ecc91148190aa820fcd466009ce |
completed | April 19, 2026, 5:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a03cc1db9e88190915f71afca4ae3e7 |
completed | May 13, 2026, 12:55 a.m. |
| NEDg | Description generation | batch_6a03cd7d38708190b91e419f15704a20 |
completed | May 13, 2026, 1:01 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a03cf14b0c081908234c628ecd3aa59 |
completed | May 13, 2026, 1:08 a.m. |
Created at: April 10, 2026, 10:36 a.m.