Triple

T22527619
Position Surface form Disambiguated ID Type / Status
Subject Nadine Labaki E556950 entity
Predicate familyName P18 FINISHED
Object Labaki
Labaki is the surname of Nadine Labaki, a prominent Lebanese filmmaker and actress known for socially engaged films such as "Caramel" and "Capernaum."
 E1542470 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: Labaki | Statement: [Nadine Labaki, familyName, Labaki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Labaki
Context triple: [Nadine Labaki, familyName, Labaki]
  • A. Oshimbalanhu
    Oshimbalanhu is a regional dialect of the Oshiwambo language cluster spoken by communities in northern Namibia and southern Angola.
  • B. Stockach
    Stockach is a small town in southern Germany’s Baden-Württemberg state, situated near Lake Constance and known historically as a regional administrative and market center.
  • C. Alakozai
    Alakozai is a Pashtun subtribe belonging to the larger Durrani tribal confederation in Afghanistan.
  • D. Pakoštane
    Pakoštane is a coastal village and popular tourist destination in Croatia, situated between the Adriatic Sea and Lake Vrana.
  • E. Kabare
    Kabare is a town in the eastern Democratic Republic of the Congo that serves as the main local hub for governance and services in its surrounding region.
  • 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: Labaki
Triple: [Nadine Labaki, familyName, Labaki]
Generated description
Labaki is the surname of Nadine Labaki, a prominent Lebanese filmmaker and actress known for socially engaged films such as "Caramel" and "Capernaum."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Labaki
Target entity description: Labaki is the surname of Nadine Labaki, a prominent Lebanese filmmaker and actress known for socially engaged films such as "Caramel" and "Capernaum."
  • A. Oshimbalanhu
    Oshimbalanhu is a regional dialect of the Oshiwambo language cluster spoken by communities in northern Namibia and southern Angola.
  • B. Stockach
    Stockach is a small town in southern Germany’s Baden-Württemberg state, situated near Lake Constance and known historically as a regional administrative and market center.
  • C. Alakozai
    Alakozai is a Pashtun subtribe belonging to the larger Durrani tribal confederation in Afghanistan.
  • D. Pakoštane
    Pakoštane is a coastal village and popular tourist destination in Croatia, situated between the Adriatic Sea and Lake Vrana.
  • E. Kabare
    Kabare is a town in the eastern Democratic Republic of the Congo that serves as the main local hub for governance and services in its surrounding region.
  • 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_69e11e57483c8190b0887c4f8ff26446 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15ed411488190a51320930b9805c2 completed April 29, 2026, 1:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b1dd894048190a50e4b3d24d26905 completed May 18, 2026, 2:10 p.m.
NEDg Description generation batch_6a0b2560f8b08190aaba573e06d38d55 completed May 18, 2026, 2:42 p.m.
NED2 Entity disambiguation (via description) batch_6a0b2729328481908faf3f88acfc9de1 completed May 18, 2026, 2:50 p.m.
Created at: April 16, 2026, 8:51 p.m.